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

Not in Any Lists

No Comments

Negative Logits

rob

-0.27

-xl

-0.27

_sb

-0.27

åī¯åİ¿éķ¿

-0.26

-semibold

-0.26

fund

-0.25

nik

-0.24

åİ¿éķ¿

-0.24

]",

-0.24

 mascul

-0.23

POSITIVE LOGITS

tech

0.32

æ¡Ĩæŀ¶

0.30

åħ³èģĶäº¤æĺĵ

0.29

otech

0.28

æĬĢ

0.26

ç¨»

0.25

.Hex

0.25

æ´¾

0.25

æ´½è°Ī

0.24

ICE

0.24

Activations Density 0.014%

No Known Activations

This feature has no known activations.