© 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 · 119089 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
119089

INDEX

Explanations

improvements

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

孱

-0.08

 ****

-0.07

cedures

-0.07

面具

-0.07

 Orders

-0.06

觿

-0.06

𬃊

-0.06

 begs

-0.06

 expensive

-0.06

 связан

-0.06

POSITIVE LOGITS

水域

0.08

ccb

0.07

ıt

0.07

 triangle

0.07

DX

0.07

هدف

0.06

死

0.06

溶解

0.06

三四

0.06

▄

0.06

Activations Density 0.113%

No Known Activations