© 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 · 19-RESID-POST-AA · 109439 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
109439

INDEX

Explanations

sites

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

苦し

-0.07

אמ

-0.07

CK

-0.07

 GmbH

-0.07

嗽

-0.07

eo

-0.07

拴

-0.07

 teased

-0.07

structures

-0.07

 investigación

-0.06

POSITIVE LOGITS

friend

0.07

'↵↵↵↵

0.07

=\

0.07

Opens

0.07

 Opens

0.07

 electoral

0.07

nej

0.07

毕业生

0.06

应急预案

0.06

men

0.06

Activations Density 0.055%

No Known Activations