© 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
Home
Qwen3.5-4B
15-RES-MATRYOSHKA-65K
22470
Prev
Next
MODEL
15-res-matryoshka-65k
Source/SAE
INDEX
Go
Explanations
ohen
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-haiku-5-5
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
decoderesearch/qwen-3.5-saes/qwen-3.5-4b
Prompts (Dashboard)
16,384 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
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/qwen3.5-4b/15-res-matryoshka-65k/22470?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/qwen3.5-4b/15-res-matryoshka-65k/22470?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Negative Logits
ences
-0.09
ecie
-0.08
kea
-0.08
resse
-0.08
ohon
-0.07
à¸Ķย
-0.07
åĮĨ
-0.07
menta
-0.07
embali
-0.07
esse
-0.07
POSITIVE LOGITS
0.07
j
0.06
1
0.06
0.06
if
0.05
(
0.05
ÛĮ
0.05
I
0.05
igh
0.05
I
0.05
Act
ivations
Density 0.184%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
