© 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 · 9580 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
9580

INDEX

Explanations

yn

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

 Raider

-0.07

 wybrać

-0.07

عائلة

-0.07

📒

-0.07

싸

-0.07

借鉴

-0.06

南瓜

-0.06

⽗

-0.06

沧桑

-0.06

🍖

-0.06

POSITIVE LOGITS

stock

0.07

-force

0.07

-stat

0.07

デ

0.07

FIN

0.07

Storage

0.07

 console

0.07

List

0.07

?'↵↵

0.07

AutoresizingMaskIntoConstraints

0.07

Activations Density 0.075%

No Known Activations