INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 involved

-0.29

ROT

-0.27

st

-0.26

aro

-0.25

 cÃ¢n

-0.24

Ron

-0.24

Mod

-0.23

 expos

-0.23

mod

-0.23

è¡¨ç¤º

-0.23

POSITIVE LOGITS

uger

0.28

iler

0.27

ngth

0.27

lems

0.26

æľŁ

0.25

zones

0.25

 Send

0.25

azine

0.24

âĪŁ

0.24

è¿Ļæ®µ

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.