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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ercul

-0.27

hours

-0.26

igy

-0.26

everyone

-0.26

.wik

-0.25

å¤§å®¶åĪĨäº«

-0.25

thÃ¨que

-0.25

StartPosition

-0.25

igkeit

-0.25

å¸ĮæľĽå¤§å®¶

-0.24

POSITIVE LOGITS

 exactly

0.31

ä¸ŃåİŁ

0.27

âĸĵ

0.26

 boolean

0.26

 fall

0.25

éŁ³

0.25

 Ritch

0.25

uan

0.24

 Remed

0.24

,↵

0.24

Activations Density 0.016%

No Known Activations

This feature has no known activations.