© 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 · 7-RESID-POST-AA · 9355 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
9355

INDEX

Explanations

ITH

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

_HIDE

-0.07

后面的

-0.07

逊

-0.07

 Donne

-0.07

Exports

-0.07

xor

-0.07

me

-0.07

panies

-0.07

 progression

-0.06

מרחב

-0.06

POSITIVE LOGITS

 окружающ

0.08

 diving

0.08

 Falcon

0.07

𝔷

0.07

 ()
↵

0.07

July

0.07

 known

0.07

 noisy

0.07

🌶

0.06

 QLabel

0.06

Activations Density 0.002%

No Known Activations