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

 enumer

-0.26

ieur

-0.25

baj

-0.24

odesk

-0.24

åĨł

-0.23

å·¾

-0.23

elden

-0.23

prÃ¼f

-0.23

imei

-0.23

å¹³æķ´

-0.22

POSITIVE LOGITS

rif

0.26

åĩºéģĵ

0.25

åħ¨éķĩ

0.25

.ix

0.25

ording

0.24

é»ĺé»ĺ

0.24

IBC

0.24

ç´¯ç´¯

0.24

âľİ

0.23

BJECT

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.