© 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 · 11-RESID-POST-AA · 30826 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
30826

INDEX

Explanations

comparisons

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

内で

-0.08

uzu

-0.07

.nb

-0.07

➡

-0.07

也不是

-0.07

_TV

-0.06

➝

-0.06

רן

-0.06

趕

-0.06

>&

-0.06

POSITIVE LOGITS

 Keith

0.07

*[

0.07

Group

0.07

(Str

0.07

Foundation

0.07

 monday

0.07

WOM

0.07

izzard

0.07

 metod

0.07

חי

0.06

Activations Density 0.010%

No Known Activations