© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
MAY 26
Assistant Axis
JAN 26
Circuit Tracer
APR 26
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
Docs
Community
Blog
Privacy & Terms
Contact
Sign In
Side-by-side compare needs a wider screen.
Open other feature
Close compare
MODEL
6-mlp
Source/SAE
Prev
Next
Go
Close
Circuit Sparsity
No connected neurons data available
Explanations
`__init__` method definition
python-code · gemini-2.5-flash-lite
No Scores
private members or methods (negative activations)
python-code · gemini-2.5-flash-lite
No Scores
Auto-Interp Tools
Generate Auto-Interp
Intrusion Detection
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
Prompts (Dashboard)
16,384 prompts, 256 tokens each
Dataset (Dashboard)
neuronpedia/python-code-simplified
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/circuitgpt-python/6-mlp/1189?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/circuitgpt-python/6-mlp/1189?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Negative Logits
(re
-0.02
£
-0.02
Ľ
-0.01
±
-0.01
²
-0.01
«
-0.01
as
-0.01
(key
-0.01
representing
-0.00
U
-0.00
Positive Logits
us
0.03
between
0.03
join
0.02
based
0.02
on
0.02
oal
0.02
by
0.02
that
0.02
_from
0.02
_by
0.02
Act
ivations
Density 64.290%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
MODEL
6-mlp
Source/SAE
Prev
Next
Go
Close
Circuit Sparsity
No connected neurons data available
Explanations
`__init__` method definition
python-code · gemini-2.5-flash-lite
No Scores
private members or methods (negative activations)
python-code · gemini-2.5-flash-lite
No Scores
Auto-Interp Tools
Generate Auto-Interp
Intrusion Detection
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
Prompts (Dashboard)
16,384 prompts, 256 tokens each
Dataset (Dashboard)
neuronpedia/python-code-simplified
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/circuitgpt-python/6-mlp/1189?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/circuitgpt-python/6-mlp/1189?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Negative Logits
(re
-0.02
£
-0.02
Ľ
-0.01
±
-0.01
²
-0.01
«
-0.01
as
-0.01
(key
-0.01
representing
-0.00
U
-0.00
Positive Logits
us
0.03
between
0.03
join
0.02
based
0.02
on
0.02
oal
0.02
by
0.02
that
0.02
_from
0.02
_by
0.02
Act
ivations
Density 64.290%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
