© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Qwen3-1.7B
27-LLAMASCOPE-2-LORSA-16K-K64
15871
Prev
Next
MODEL
27-llamascope-2-lorsa-16k-k64
Source/SAE
INDEX
Go
Explanations
say deception
unknown · unknown
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
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-k64/15871?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-k64/15871?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
瑗
-16.00
сон
-16.00
囡
-15.63
班车
-15.56
首都
-15.44
UPPORT
-15.38
ussed
-15.31
网站地图
-15.25
煦
-15.13
OCUS
-15.06
POSITIVE LOGITS
欺骗
38.25
fake
36.25
骗
35.75
deception
35.00
(fake
33.50
骗局
33.25
Fake
33.25
欺诈
33.00
fake
32.75
诈
32.50
Act
ivations
Density 0.546%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
