INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ystone

-0.29

çªĴ

-0.27

turnstile

-0.27

lays

-0.26

onis

-0.26

*__

-0.25

cycles

-0.24

 rÃ©gime

-0.23

éĹ¨åīį

-0.23

(CancellationToken

-0.23

POSITIVE LOGITS

ãģªãĤĭ

0.28

ja

0.26

 Barb

0.25

èĩ¾

0.24

aur

0.24

fter

0.24

åı¯è¡Į

0.24

esson

0.24

 astr

0.24

 submit

0.24

Activations Density 0.142%

No Known Activations

This feature has no known activations.