© 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
Qwen3-14B
20-RESID-BATCHTOPK-65K__L0-80
10697
Prev
Next
MODEL
20-resid-batchtopk-65k__l0-80
Source/SAE
INDEX
Go
Explanations
numeric or symbolic sequences
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
Prompts (Dashboard)
16,384 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/qwen3-14b/20-resid-batchtopk-65k__l0-80/10697?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/qwen3-14b/20-resid-batchtopk-65k__l0-80/10697?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
æī§æĶ¿
-0.20
lo
-0.20
pur
-0.19
tr
-0.19
j
-0.19
çİ©
-0.19
éĻ©
-0.18
ent
-0.18
lo
-0.18
w
-0.18
POSITIVE LOGITS
é¹ŀ
0.21
ndx
0.20
è£Ļ
0.19
é¹ĥ
0.19
éªħ
0.19
xdb
0.19
èĬ±èįī
0.19
xBA
0.19
诽
0.18
ToWorld
0.18
Act
ivations
Density 0.306%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
