© 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 · 11-RESID-POST-AA · 108719 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
108719

INDEX

Explanations

Foreign languages and film

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

)+"

-0.07

驲

-0.07

เท

-0.06

 ?>
↵

-0.06

苔

-0.06

 PhpStorm

-0.06

 benefits

-0.06

 skype

-0.06

\xe

-0.06

AnimationsModule

-0.06

POSITIVE LOGITS

ZF

0.07

واء

0.07

chunks

0.07

zf

0.07

dü

0.07

 bustling

0.07

dził

0.06

yk

0.06

Upper

0.06

FUL

0.06

Activations Density 0.130%

No Known Activations