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

çĤ¹ç¼Ģ

-0.27

aar

-0.25

èĢħçļĦ

-0.25

çł§

-0.24

URRENCY

-0.24

(&(

-0.24

esser

-0.23

 bÃ¨

-0.23

(QL

-0.23

æĲŃå»º

-0.23

POSITIVE LOGITS

ograms

0.28

á»ĩt

0.26

NotFoundException

0.25

Working

0.24

robe

0.24

 Obst

0.24

working

0.24

ÐµÐ½Ð½Ð¾

0.23

æī¿

0.23

extract

0.23

Activations Density 10.773%

No Known Activations

This feature has no known activations.