© 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 · 11-RESID-POST-AA · 96179 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
96179

INDEX

Explanations

possessive pronouns

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

iode

-0.07

;?>↵

-0.07

ingo

-0.07

 subdivisions

-0.07

.intro

-0.07

_CAPTURE

-0.07

慨

-0.07

product

-0.06

awl

-0.06

 Shannon

-0.06

POSITIVE LOGITS

casts

0.07

_DEV

0.07

.LocalDate

0.07

 自动生成

0.06

FIG

0.06

 Byte

0.06

.GetFileName

0.06

_a

0.06

(TypeError

0.06

器官

0.06

Activations Density 0.040%

No Known Activations