© 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
26-LLAMASCOPE-2-LORSA-16K-K64
2133
Prev
Next
MODEL
26-llamascope-2-lorsa-16k-k64
Source/SAE
INDEX
Go
Explanations
标识
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/26-llamascope-2-lorsa-16k-k64/2133?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/26-llamascope-2-lorsa-16k-k64/2133?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
cur
-25.50
pen
-24.13
万
-23.50
曲
-21.75
config
-20.88
萬
-20.88
Mill
-20.75
=config
-20.63
cur
-20.50
cur
-20.38
POSITIVE LOGITS
标识
26.75
注
20.75
Ben
20.25
Ben
19.38
标注
18.63
[idx
18.50
margins
18.13
註
17.88
(ctx
17.63
Marc
17.63
Act
ivations
Density 0.085%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
