Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Qwen3-4B
7-TRANSCODER-HP
130237
Prev
Next
MODEL
7-transcoder-hp
Source/SAE
INDEX
Go
Explanations
in
np_max-act · 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_7.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.7.mlp.hook_in
Architecture
transcoder
Context Size
8,192
Dataset
monology/pile-uncopyrighted
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/qwen3-4b/7-transcoder-hp/130237?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/qwen3-4b/7-transcoder-hp/130237?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
DG
-0.25
eg
-0.25
DG
-0.25
EG
-0.25
itu
-0.25
roup
-0.25
yg
-0.25
éĮ¢
-0.24
7
-0.24
EN
-0.24
POSITIVE LOGITS
ATV
0.30
ideally
0.29
èĹ©
0.26
te
0.25
sez
0.25
Locator
0.25
ira
0.24
erra
0.24
æłĩ
0.23
unbind
0.23
Act
ivations
Density 0.003%
Test
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
