© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 70561 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
70561

INDEX

Explanations

meiosis

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

(vertices

-0.07

 bloggers

-0.07

_ALREADY

-0.07

 mentally

-0.07

 pedigree

-0.07

保住

-0.07

 true

-0.07

在路上

-0.07

记录

-0.07

 teammates

-0.07

POSITIVE LOGITS

BAS

0.07

	State

0.07

Boss

0.07

 ağrı

0.06

 Lecture

0.06

aria

0.06

.DataType

0.06

峰会

0.06

Eis

0.06

olia

0.06

Activations Density 0.007%

No Known Activations