INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

è¿

-0.26

åĨĴéĻ©

-0.25

bia

-0.25

.executor

-0.25

reno

-0.24

 cutting

-0.24

 cruc

-0.23

åĨĴ

-0.23

 jury

-0.23

wal

-0.23

POSITIVE LOGITS

xFFFF

0.25

aved

0.25

etty

0.25

çªł

0.24

å®¤å¤ĸ

0.24

addContainerGap

0.23

å¥½äºº

0.23

OMEM

0.23

)__

0.23

("{\"

0.23

Activations Density 0.007%

No Known Activations

This feature has no known activations.