© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 20-MATRYOSHKA-CHAT-65K · 46556 ｜ Neuronpedia

Home
Qwen2.5-7B-IT
20-MATRYOSHKA-CHAT-65K
46556

INDEX

Explanations

database

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/lmsys/matryoshka/k-100

Prompts (Dashboard)

16,384 prompts, 192 tokens each

Dataset (Dashboard)

chanind/lmsys-chat-1m-qwen-2.5

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âĦħ

-0.32

*****č↵

-0.27

çĶŃ

-0.27

âĹĦ

-0.26

 <!--[

-0.26

GPC

-0.24

QS

-0.24

ï¸°

-0.24

 AudioClip

-0.24

%!

-0.23

POSITIVE LOGITS

-strokes

0.29

ngth

0.26

upos

0.26

tsy

0.26

istros

0.25

pson

0.23

 impover

0.23

ween

0.23

ãģ«æĪ

0.23

venes

0.23

Activations Density 0.013%

No Known Activations