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

 theirs

-0.28

æ¶Īè´¹èĢħçļĦ

-0.27

ovich

-0.27

linky

-0.25

.createComponent

-0.24

Ã©sz

-0.24

_DX

-0.24

rÃ¼ck

-0.24

 wounds

-0.24

 sided

-0.23

POSITIVE LOGITS

ker

0.27

åĻ«

0.26

'll

0.24

 Canada

0.23

Cat

0.23

iveness

0.23

åĨħæ¶µ

0.23

 clen

0.23

èĦĺ

0.22

etermined

0.22

Activations Density 0.001%

No Known Activations

This feature has no known activations.