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

æĻļ

-0.28

æıĲé«ĺ

-0.25

/Runtime

-0.24

ewood

-0.24

 TimeUnit

-0.24

ªĮ

-0.24

ropdown

-0.24

å¼Ģè½¦

-0.24

ä¼ļä¸Ĭ

-0.23

ijk

-0.23

POSITIVE LOGITS

cko

0.29

 exact

0.27

è¯¥æĢİä¹ĪåĬŀ

0.26

//=

0.26

las

0.26

marked

0.26

 pres

0.25

åħ¬çĶ¨

0.25

unos

0.25

 Stamp

0.25

Activations Density 0.024%

No Known Activations

This feature has no known activations.