© 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
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Qwen3-1.7B
27-LLAMASCOPE-2-LORSA-16K-K64
15086
Prev
Next
MODEL
27-llamascope-2-lorsa-16k-k64
Source/SAE
INDEX
Go
Explanations
say "two-letter abbreviations"
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-k64/15086?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-k64/15086?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
patch
-17.00
app
-16.63
窍
-15.69
袜
-15.69
platform
-15.63
app
-15.25
spree
-15.06
ück
-14.75
op
-14.69
Sp
-14.50
POSITIVE LOGITS
(lp
24.88
(LP
24.75
lp
23.50
TP
23.38
(KP
23.25
(tp
22.50
(bp
22.13
LP
22.00
,tp
21.75
BP
21.63
Act
ivations
Density 0.206%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
