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

shy

-0.27

çªľ

-0.26

PKK

-0.26

æī¹å¤į

-0.25

 stern

-0.24

guns

-0.24

 harmon

-0.23

iams

-0.23

umps

-0.23

asers

-0.23

POSITIVE LOGITS

Vict

0.25

 Guard

0.25

çĶŁåĳ½åĬĽ

0.25

CO

0.24

#:

0.24

NT

0.24

 UNUSED

0.24

 vision

0.24

æĻºåĬĽ

0.24

ben

0.24

Activations Density 0.263%

No Known Activations

This feature has no known activations.