© 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
Home
Qwen3-4B
27-TRANSCODER-HP
57492
Prev
Next
MODEL
27-transcoder-hp
Source/SAE
INDEX
Go
Explanations
Code snippets
np_max-act-logits · gemini-2.0-flash
No Scores
code blocks and code-related syntax (brackets, semicolons, method definitions, etc.) in technical documentation or programming-related queries.
oai_token-act-pair · deepseek-v3
Triggered by @finnwit
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
mwhanna/qwen3-4b-transcoders/layer_27.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.27.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/27-transcoder-hp/57492?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/27-transcoder-hp/57492?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
ä¼
-0.30
SplitOptions
-0.28
UsageId
-0.26
éŁŃ
-0.26
qrt
-0.25
arie
-0.25
FINITY
-0.24
полÑĥ
-0.24
oram
-0.23
æĦĶ
-0.23
POSITIVE LOGITS
↵↵
0.54
↵
0.52
↵
0.50
č↵č↵
0.43
č↵
0.42
↵↵
0.42
č
0.40
čč↵
0.40
↵↵
0.38
č↵
0.38
Act
ivations
Density 0.039%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations