© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
CIRCUITGPT-PYTHON · 7-RESID · 249 ｜ Neuronpedia
Home
OpenAI · Weight-Sparse Transformers
CircuitGPT-Python
Residual Stream
7-RESID
249
Prev
Next
MODEL
7-resid
Source/SAE
INDEX
Go
Explanations
defaultdict or deque constructor
python-code · gemini-2.5-flash-lite
No Scores
closing parenthesis and bracket (negative activations)
python-code · gemini-2.5-flash-lite
No Scores
New Auto-Interp
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/7-resid/249?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/7-resid/249?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
9
-0.20
59
-0.19
90
-0.18
10
-0.13
S
-0.08
11
-0.05
m
-0.04
'
0.00
#
0.00
&
0.00
POSITIVE LOGITS
xp
0.21
import
0.19
unc
0.16
ati
0.13
ub
0.12
ri
0.12
/
0.10
<|
0.10
pro
0.09
i
0.08
Act
ivations
Density 100.000%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
