© 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

QWEN3.5-4B · 15-RES-MATRYOSHKA-65K · 19085 ｜ Neuronpedia

Home
Qwen3.5-4B
15-RES-MATRYOSHKA-65K
19085

INDEX

Explanations

countries and places

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

decoderesearch/qwen-3.5-saes/qwen-3.5-4b

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

-0.06

dan

-0.06

pro

-0.05

ala

-0.05

comp

-0.05

conse

-0.05

-0.05

ħ

-0.05

ä»Ģä¹Īæĺ¯

-0.05

yper

-0.05

POSITIVE LOGITS

eke

0.07

orsi

0.07

oriously

0.07

ÑģÑĤÐµÑģÑĤÐ²ÐµÐ½Ð½Ð¾

0.07

acionamento

0.06

 estrang

0.06

uzzi

0.06

rael

0.06

 pouc

0.06

ç©º

0.06

Activations Density 0.005%

No Known Activations