© 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 · 80479 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
80479

INDEX

Explanations

Keys

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

_lifetime

-0.08

oming

-0.07

动作

-0.06

Clip

-0.06

 coup

-0.06

_WARNING

-0.06

 Bour

-0.06

 emotional

-0.06

嘴角

-0.06

ขอบ

-0.06

POSITIVE LOGITS

zept

0.07

 keys

0.07

 JavaScript

0.07

 supermarket

0.07

示

0.06

 UIKit

0.06

ytt

0.06

领导下

0.06

-ranked

0.06

 clerk

0.06

Activations Density 0.006%

No Known Activations