© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

QWEN2.5-7B-IT · 15-RESID-POST-AA · 44721 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
44721

INDEX

Explanations

Dialogue

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

 gezocht

-0.07

パー�

-0.07

EMP

-0.07

ブル

-0.07

岙

-0.07

 Shopping

-0.06

GROUND

-0.06

 saver

-0.06

蔬

-0.06

ORIES

-0.06

POSITIVE LOGITS

 project

0.07

=event

0.07

hj

0.06

_sz

0.06

]}"

0.06

 crow

0.06

pin

0.06

osity

0.06

_radi

0.06

✥

0.06

Activations Density 0.088%

No Known Activations