SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1506.06579 · 2015

Understanding Neural Networks Through Deep Visualization

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1506.06579.json · badge: /api/ran/1506.06579.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
yosinski/deep-visualization-toolbox community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 2 no recorded run
FunctionStatusWhere it lives
norm01 Ran
ran on a synthesized input
yosinski/deep-visualization-toolbox/image_misc.py
code served (permissive licence) · get_code("6762ed67b457b459")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

torch.manual_seed(0)

# The function norm01 takes an array-like object and:
# 1. Calls .copy() on it
# 2. Calls .min() on it
# 3. Calls .max() on it
# 4. Supports subtraction and division operations
# This works with numpy arrays

arr = np.array([[1.0, 2.0, 3.0, 4.0],
                [5.0, 6.0, 7.0, 8.0]])

ARGS = {
    "arr": arr
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
norm01c Ran
ran on a synthesized input
yosinski/deep-visualization-toolbox/image_misc.py
code served (permissive licence) · get_code("67b35185a0eda163")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function norm01c takes:
# - arr: a numpy array that supports .copy(), -, /=, .max(), .min(), += operations
# - center: a scalar value used to center the array

# Create a small numpy array with some values
arr = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

# Choose a center value (typically somewhere in the middle of the data range)
center = 3.0

ARGS = {
    "arr": arr,
    "center": center,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (5,) — shape (5,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
norm0255 Ran
ran on a synthesized input
yosinski/deep-visualization-toolbox/image_misc.py
code served (permissive licence) · get_code("274ea775ee06d4bf")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family int, shape (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function norm0255 takes an array and normalizes it to [0, 255] as uint8
# It calls: arr.copy(), arr.min(), arr.max(), and converts to uint8
# So we need a numpy array with numeric values

arr = np.array([[10.5, 20.3, 15.7], [5.2, 8.9, 12.1]], dtype=np.float32)

ARGS = {
    'arr': arr
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_image Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from KamitaniLab/cnnpref
pointer only · get_code("b43d90577686455e")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

generate_image Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from KamitaniLab/cnnpref
pointer only · get_code("f4b8e2487402d23c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
generate_image 3 other papers
1 dated earlier, 2 later
1312.6034 (2013-12)
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
1602.02644 (2016-02)
Generating Images with Perceptual Similarity Metrics based on Deep Networks
1605.09304 (2016-05)
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
generate_image 2 other papers
2 later
1602.02644 (2016-02)
Generating Images with Perceptual Similarity Metrics based on Deep Networks
1605.09304 (2016-05)
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent years have produced great advances in training large, deep neural networks (DNNs), including notable successes in training convolutional neural networks (convnets) to recognize natural images. However, our understanding of how these models work, especially what computations they perform at intermediate layers, has lagged behind. Progress in the field will be further accelerated by the development of better tools for visualizing and interpreting neural nets. We introduce two such tools here. The first is a tool that visualizes the activations produced on each layer of a trained convnet as it processes an image or video (e.g. a live webcam stream). We have found that looking at live activations that change in response to user input helps build valuable intuitions about how convnets work. The second tool enables visualizing features at each layer of a DNN via regularized optimization in image space. Because previous versions of this idea produced less recognizable images, here we introduce several new regularization methods that combine to produce qualitatively clearer, more interpretable visualizations. Both tools are open source and work on a pre-trained convnet with minimal setup.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1506.06579")
get_code_for_paper("1506.06579")
have("1506.06579")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1506.06579.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1506.06579.svg)](https://syntology.ai/paper/1506.06579)

Connect an agent — have() is free.