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
30-TRANSCODER-HP
15185
Prev
Next
MODEL
30-transcoder-hp
Source/SAE
INDEX
Go
Explanations
hyphen
np_max-act-logits · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
Prompts (Dashboard)
16,384 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/qwen3-4b/30-transcoder-hp/15185?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/qwen3-4b/30-transcoder-hp/15185?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
-X
-0.28
venta
-0.27
âĢ¦and
-0.27
=z
-0.25
ï¼Įé»ĺ认
-0.25
ï¼Į请
-0.25
=id
-0.25
=search
-0.25
/kg
-0.25
zp
-0.25
POSITIVE LOGITS
s
0.48
I
0.36
T
0.33
t
0.32
d
0.31
a
0.31
sites
0.30
n
0.30
x
0.29
Ter
0.29
Act
ivations
Density 0.232%
Test
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
