© 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 · 74712 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
74712

INDEX

Explanations

.exec

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

dbcTemplate

-0.08

銎

-0.07

lid

-0.07

╙

-0.07

 sole

-0.07

盎

-0.07

 composed

-0.07

筥

-0.07

主持人

-0.07

🌳

-0.07

POSITIVE LOGITS

拼音

0.08

 glasses

0.07

BMI

0.07

tra

0.07

_NORMAL

0.07

 courtesy

0.07

פגישה

0.07

 حاجة

0.07

_UID

0.06

 fant

0.06

Activations Density 0.000%

No Known Activations