© 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
QWEN3-32B · MLP Neurons - Layer 23 · 20654 ｜ Neuronpedia
Home
Qwen3-32B
MLP Neurons - Layer 23
20654
Prev
Next
MODEL
Neurons Layer 23
Layer 22
Layer 24
INDEX
Go
Explanations
Words like "possible," "happened," and "better" that express a desired outcome or state.
eleuther_acts_top20 · gemini-2.5-flash-lite
Triggered by @paultiplady
No Scores
numbers
np_max-act-logits · gemini-2.5-flash-lite
Triggered by @paultiplady
No Scores
Common suffixes and abstract concepts
np_min-act-logits · gemini-2.5-flash-lite
Neg Acts
Triggered by @paultiplady
No Scores
possible
np_max-act · gemini-2.5-flash-lite
Triggered by @paultiplady
No Scores
words related to potential and success.
oai_token-act-pair · gemini-2.5-flash-lite
Triggered by @paultiplady
No Scores
New Auto-Interp
AutoInterp Type
claude-haiku-5-5
Generate
Top Features by Cosine Similarity
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/qwen3-32b/23/20654?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/qwen3-32b/23/20654?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Loading dashboard...
