© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 125038 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
125038

INDEX

Explanations

certification

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

承

-0.08

_svg

-0.07

."

-0.07

流水

-0.06

 aspect

-0.06

 Validators

-0.06

_setting

-0.06

弦

-0.06

år

-0.06

handleChange

-0.06

POSITIVE LOGITS

eliminar

0.07

נפל

0.07

incess

0.07

会觉得

0.07

觉醒

0.07

 arsch

0.07

 Preferred

0.07

ModelIndex

0.07

厚重

0.06

 też

0.06

Activations Density 0.001%

No Known Activations