© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

QWEN2.5-7B-IT · 11-RESID-POST-AA · 29471 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
29471

INDEX

Explanations

Samoa

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

อม

-0.08

 covariance

-0.07

wechat

-0.07

当て

-0.07

displayText

-0.07

怆

-0.07

 empathy

-0.07

 Cush

-0.07

互利

-0.07

 derby

-0.07

POSITIVE LOGITS

ANTA

0.08

казывает

0.08

 GENERAL

0.07

 ()↵↵

0.07

民眾

0.07

 hombres

0.07

本报讯

0.07

0.06

磊

0.06

SSION

0.06

Activations Density 0.002%

No Known Activations