INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 Jord

-0.27

 Disk

-0.27

IZES

-0.26

illed

-0.26

 naked

-0.25

åĹĵ

-0.25

dess

-0.25

?:

-0.25

izable

-0.25

 Vand

-0.24

POSITIVE LOGITS

å¿½

0.26

minster

0.26

çļĦç¬¬ä¸Ģä¸ª

0.26

æ´¹

0.25

yc

0.25

ATA

0.25

çķĻ

0.25

thon

0.25

_clock

0.25

ftar

0.24

Activations Density 0.245%

No Known Activations

This feature has no known activations.