© 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 · 15-RESID-POST-AA · 120936 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
120936

INDEX

Explanations

Information

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

�

-0.08

甚

-0.07

 Viagra

-0.07

 suggesting

-0.07

otor

-0.06

_NOT

-0.06

Streaming

-0.06

 nominees

-0.06

 Marian

-0.06

决

-0.06

POSITIVE LOGITS

 inclus

0.07

(inputStream

0.07

'field

0.07

.clean

0.07

pe

0.07

汧

0.06

淄博

0.06

嫡

0.06

 الكلام

0.06

bru

0.06

Activations Density 0.013%

No Known Activations