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

Not in Any Lists

No Comments

Negative Logits

uster

-0.28

lick

-0.27

orf

-0.27

.LayoutParams

-0.26

Ð¿Ð¸ÑĤ

-0.25

related

-0.25

ä½ıäºĨ

-0.25

æİ¥è§¦

-0.24

ä¸įä½ı

-0.24

bart

-0.24

POSITIVE LOGITS

 tease

0.28

/english

0.27

cra

0.27

lan

0.26

 Samsung

0.25

LAN

0.25

Ã½

0.25

'||

0.25

PC

0.24

 lanc

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.