© 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 · 7-RESID-POST-AA · 102906 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
102906

INDEX

Explanations

ket

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

 صح

-0.08

蹀

-0.07

 massages

-0.07

 günümüz

-0.07

ถา

-0.07

 Mormon

-0.07

FAILED

-0.07

",[

-0.07

 evidenced

-0.07

dab

-0.07

POSITIVE LOGITS

cdot

0.08

 Albany

0.08

ше

0.08

.ActionEvent

0.07

 perme

0.07

angle

0.07

plen

0.07

ина

0.07

分流

0.07

 offre

0.06

Activations Density 0.002%

No Known Activations