© 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 · 95688 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
95688

INDEX

Explanations

lowest

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

-am

-0.07

woo

-0.07

erts

-0.07

pour

-0.06

 Gang

-0.06

ʋ

-0.06

our

-0.06

Ŧ

-0.06

흄

-0.06

珊

-0.06

POSITIVE LOGITS

_sensitive

0.07

КА

0.07

 obliv

0.07

 strchr

0.07

书法

0.07

全面落实

0.07

 resize

0.06

 stati

0.06

vik

0.06

Writing

0.06

Activations Density 0.001%

No Known Activations