© 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 · 76122 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
76122

INDEX

Explanations

<

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

-destruct

-0.08

FLICT

-0.07

.bias

-0.07

 ldap

-0.07

삥

-0.07

 предусмотр

-0.06

不断发展

-0.06

_LOOP

-0.06

管辖

-0.06

ADE

-0.06

POSITIVE LOGITS

 соб

0.07

Widget

0.07

 Columbus

0.07

 stream

0.07

，↵

0.07

 unions

0.06

_tuple

0.06

 Closure

0.06

的设计

0.06

₥

0.06

Activations Density 0.002%

No Known Activations