© 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 · 20990 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
20990

INDEX

Explanations

://

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

Gio

-0.08

 CreateTable

-0.07

Immutable

-0.07

 assertTrue

-0.07

陴

-0.06

 magma

-0.06

🌚

-0.06

.mit

-0.06

ıyordu

-0.06

č

-0.06

POSITIVE LOGITS

Four

0.07

_winner

0.07

enchmark

0.07

(agent

0.07

昨晚

0.06

 baseman

0.06

磊

0.06

е

0.06

[m

0.06

혜

0.06

Activations Density 0.002%

No Known Activations