© 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 · 9797 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
9797

INDEX

Explanations

articles

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

 Transmit

-0.07

溲

-0.07

_LOADED

-0.06

ㅗ

-0.06

etSocketAddress

-0.06

.ObjectMeta

-0.06

科创板

-0.06

usuarios

-0.06

WK

-0.06

.Listener

-0.06

POSITIVE LOGITS

遊

0.07

=line

0.07

……↵↵

0.06

现已

0.06

(("

0.06

 przecież

0.06

幻想

0.06

 Luna

0.06

県

0.06

****↵

0.06

Activations Density 0.182%

No Known Activations