© 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 · 71107 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
71107

INDEX

Explanations

quicksort algorithm

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

 yüz

-0.08

 twisted

-0.07

 numberWith

-0.07

 właściciel

-0.07

outlined

-0.07

榈

-0.07

 "+↵

-0.07

jspx

-0.07

 licz

-0.07

 Chancellor

-0.07

POSITIVE LOGITS

离开

0.07

 Never

0.07

.assertNot

0.07

Never

0.06

_closed

0.06

䓛

0.06

尽力

0.06

されます

0.06

莫

0.06

//'

0.06

Activations Density 0.006%

No Known Activations