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

çĭ¬ç«ĭ

-0.28

Experts

-0.28

ÑģÑĤÑĭ

-0.26

áº§m

-0.24

æ²Ļ

-0.24

åľ¨çº¿

-0.23

è½³

-0.23

estro

-0.23

-preview

-0.23

éľ²

-0.23

POSITIVE LOGITS

éĸĵãģ«

0.28

 sections

0.26

cest

0.25

å¾¼

0.25

AH

0.25

bog

0.25

é²ĩ

0.24

 negate

0.24

.GetAsync

0.24

à²¹

0.23

Activations Density 0.006%

No Known Activations

This feature has no known activations.