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

tele

-0.27

....

-0.26

ngo

-0.26

kers

-0.26

ric

-0.24

rc

-0.24

 Ð´ÐµÑıÑĤÐµÐ»ÑĮÐ½Ð¾ÑģÑĤÑĮ

-0.24

...",↵

-0.23

.Dock

-0.23

Boundary

-0.23

POSITIVE LOGITS

edith

0.29

åĬŀ

0.28

Zus

0.26

BarButton

0.25

zag

0.24

clip

0.24

quisites

0.24

ä¼¼çļĦ

0.24

agation

0.23

quisite

0.23

Activations Density 0.094%

No Known Activations

This feature has no known activations.