© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 20-MATRYOSHKA-65K · 2313 ｜ Neuronpedia

Home
Qwen2.5-7B-IT
20-MATRYOSHKA-65K
2313

INDEX

Explanations

Even

np_max-act-logits · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/inet

-0.27

¡´

-0.24

 tats

-0.23

aeda

-0.23

(',',$

-0.23

IENTATION

-0.22

();++

-0.22

/Dk

-0.22

-Compatible

-0.21

_valor

-0.21

POSITIVE LOGITS

 though

0.35

though

0.26

nia

0.24

 Though

0.24

çĴ

0.23

tho

0.22

äºĨå¥½å¤ļ

0.22

 koje

0.21

å¦į

0.21

Though

0.21

Activations Density 0.074%

No Known Activations