INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĲİç¼©

-0.26

 liters

-0.26

ç¿©

-0.25

QRST

-0.25

å²

-0.25

ç®į

-0.24

å¤±

-0.24

ë©¸

-0.24

åİĭæĬĳ

-0.23

 hollow

-0.23

POSITIVE LOGITS

ä¿¡æģ¯

0.27

å®ĩ

0.26

ä¸ĢåĲį

0.25

aba

0.25

unity

0.25

etz

0.25

(+

0.24

Safety

0.24

ä¸Ģç¬ĳ

0.24

emory

0.24

Activations Density 0.090%

No Known Activations

This feature has no known activations.