INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lia

-0.26

!--

-0.26

vet

-0.25

 brainstorm

-0.24

çĮ´

-0.24

UGH

-0.24

iph

-0.23

extends

-0.23

--

-0.23

Ĩµ

-0.23

POSITIVE LOGITS

åĢĵ

0.28

osl

0.26

nock

0.26

åĵģåĳ³

0.25

éªļ

0.25

åĲ¸åıĸ

0.24

å½ķåĥı

0.24

ä¸įå¾Ĺä¸į

0.24

-sn

0.24

-slider

0.24

Activations Density 0.065%

No Known Activations

This feature has no known activations.