© 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 · 3231 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
3231

INDEX

Explanations

Publisher

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

 deepcopy

-0.08

ny

-0.08

pickle

-0.08

dynamic

-0.07

_nm

-0.07

.doc

-0.07

Lf

-0.07

_ast

-0.07

 Agile

-0.07

(timestamp

-0.07

POSITIVE LOGITS

Gatt

0.07

acons

0.07

健身房

0.07

 leds

0.06

EFF

0.06

IEWS

0.06

랜

0.06

旅游局

0.06

 purchaser

0.06

ство

0.06

Activations Density 0.003%

No Known Activations