© 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
Qwen3-1.7B
27-LLAMASCOPE-2-LORSA-16K-K64
15556
Prev
Next
MODEL
27-llamascope-2-lorsa-16k-k64
Source/SAE
INDEX
Go
Explanations
say Chinese characters
unknown · unknown
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/qwen3-1.7b/27-llamascope-2-lorsa-16k-k64/15556?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/qwen3-1.7b/27-llamascope-2-lorsa-16k-k64/15556?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
FO
-27.38
oron
-27.13
oro
-27.13
HO
-27.00
olo
-26.88
POR
-26.88
POR
-26.75
KO
-26.38
oco
-25.88
bos
-25.88
POSITIVE LOGITS
颉
16.00
薤
15.94
失信
15.31
戚
15.19
讷
15.13
伧
15.06
labelText
14.94
喇
14.81
yne
14.75
icas
14.69
Act
ivations
Density 5.329%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
