© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 30353 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
30353

INDEX

Explanations

Christmas

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

ActivityIndicatorView

-0.07

lete

-0.07

Enh

-0.06

!("{

-0.06

 Beds

-0.06

(de

-0.06

vents

-0.06

兜

-0.06

痉

-0.06

 תע

-0.06

POSITIVE LOGITS

莫斯

0.08

_existing

0.07

KeyDown

0.07

עמי

0.07

0.07

女朋友

0.07

_leader

0.07

 Malcolm

0.07

_calendar

0.07

 filmed

0.07

Activations Density 0.003%

No Known Activations