© 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
16219
Prev
Next
MODEL
27-llamascope-2-lorsa-16k-k64
Source/SAE
INDEX
Go
Explanations
say non-Latin
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-k64/16219?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-k64/16219?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
马克
-25.13
chrom
-20.88
Chrom
-20.25
UPC
-20.00
Roch
-19.75
SCN
-19.50
chrom
-19.38
特派员
-19.13
Xavier
-19.00
ска
-19.00
POSITIVE LOGITS
翼
24.38
梓
20.25
口袋
20.00
Wing
19.75
丛林
19.63
慈
19.50
走廊
19.13
wing
19.00
竹
18.88
鸡肉
18.88
Act
ivations
Density 4.771%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
