© 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 · 42210 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
42210

INDEX

Explanations

ONE

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

 Morris

-0.07

 MutableList

-0.06

/tasks

-0.06

 Publications

-0.06

净水

-0.06

jie

-0.06

 próximo

-0.06

逆行

-0.06

 hari

-0.06

='".

-0.06

POSITIVE LOGITS

стер

0.07

 ciné

0.07

умент

0.07

 shining

0.07

Sugar

0.07

kończ

0.07

 peasant

0.07

 coer

0.07

лен

0.06

(sym

0.06

Activations Density 0.004%

No Known Activations