INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ¢¯éĺŁ

-0.33

MLM

-0.27

æĪĲä¸ºä¸ŃåĽ½

-0.26

ÅĽci

-0.26

UNS

-0.25

á»ħ

-0.25

æĪĲç«ĭä»¥æĿ¥

-0.25

èģĶç³»æĪĳä»¬

-0.25

 synd

-0.24

dov

-0.24

POSITIVE LOGITS

kees

0.31

curity

0.28

å¤ľ

0.26

 night

0.26

æĽ¿

0.24

èĭĶ

0.24

é¹

0.23

-night

0.23

éĺ²

0.23

éĨī

0.23

Activations Density 0.280%

No Known Activations

This feature has no known activations.