© 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
QWEN3-4B · 35-TRANSCODER-HP · 39581 ｜ Neuronpedia
Home
Qwen3-4B
35-TRANSCODER-HP
39581
Prev
Next
MODEL
35-transcoder-hp
Source/SAE
INDEX
Go
Explanations
ID
np_max-act-logits · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
mwhanna/qwen3-4b-transcoders/layer_35.safetensors
How To Load
Prompts (Dashboard)
16,384 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
163,840
Data Type
float32
Hook Name
blocks.35.mlp.hook_in
Architecture
transcoder
Context Size
8,192
Dataset
monology/pile-uncopyrighted
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/qwen3-4b/35-transcoder-hp/39581?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/qwen3-4b/35-transcoder-hp/39581?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
t
-0.94
tat
-0.56
tam
-0.56
té
-0.56
tur
-0.56
tal
-0.55
tas
-0.53
tica
-0.52
tic
-0.48
tin
-0.48
POSITIVE LOGITS
T
0.42
R
0.32
ed
0.30
TZ
0.28
Cx
0.28
TU
0.27
RON
0.27
ivr
0.26
C
0.26
ivas
0.25
Act
ivations
Density 0.722%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
