© 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 · 75998 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
75998

INDEX

Explanations

en

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

ethyl

-0.08

生机

-0.07

.layoutControlItem

-0.07

�

-0.06

机体

-0.06

 drug

-0.06

欹

-0.06

אמין

-0.06

 المحلي

-0.06

 characteristic

-0.06

POSITIVE LOGITS

Menu

0.07

數據

0.07

 Offer

0.07

🏗

0.07

超强

0.07

 Instructions

0.07

 Couple

0.07

 Routes

0.07

 RESERVED

0.07

cen

0.07

Activations Density 0.010%

No Known Activations