© 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 · 15-RESID-POST-AA · 121364 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
121364

INDEX

Explanations

F

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

áo

-0.07

dj

-0.07

grese

-0.07

 super

-0.07

enson

-0.07

ですし

-0.07

enz

-0.07

深夜

-0.07

ccione

-0.07

 volte

-0.06

POSITIVE LOGITS

 הית

0.07

 timedelta

0.07

 Helena

0.07

IS

0.07

_CRITICAL

0.07

 anterior

0.07

솬

0.06

 gerçek

0.06

洛

0.06

Rua

0.06

Activations Density 0.003%

No Known Activations