© 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 · 30287 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
30287

INDEX

Explanations

Legal professionals

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

approx

-0.08

 PropTypes

-0.07

parseInt

-0.07

Palette

-0.07

 olive

-0.06

 Astr

-0.06

rio

-0.06

估

-0.06

isEmpty

-0.06

 dive

-0.06

POSITIVE LOGITS

/">

0.07

 CGRect

0.07

 userdata

0.07

so

0.07

邃

0.07

 sonra

0.07

öst

0.06

 הקו

0.06

新一轮

0.06

 Voter

0.06

Activations Density 0.098%

No Known Activations