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

<Props

-0.26

åŁºçŁ³

-0.25

-share

-0.25

çŃĶåį·

-0.25

lica

-0.25

è¿ĩå¤§

-0.25

è±ĨèħĲ

-0.24

iral

-0.24

 firma

-0.24

compose

-0.23

POSITIVE LOGITS

ali

0.29

mpp

0.27

å¤Ħå¤Ħ

0.27

éĺ³åı°

0.27

omm

0.26

 setC

0.25

azi

0.25

å°½

0.25

åłķ

0.24

åºĶåľ¨

0.24

Activations Density 7.938%

No Known Activations

This feature has no known activations.