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

indre

-0.26

udder

-0.25

zb

-0.24

èªī

-0.24

çī¡ä¸¹

-0.23

åĨ¢

-0.23

 Rack

-0.23

åı¯æĢķçļĦ

-0.23

å¤¸å¼ł

-0.23

Budget

-0.22

POSITIVE LOGITS

äº¤æµģ

0.25

çĽ´

0.25

 Passage

0.24

belt

0.24

{{

0.24

åĩĨ

0.23

ä¸Ģæł·çļĦ

0.23

shell

0.23

 stout

0.23

 Narr

0.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.