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

Nor

-0.26

liqu

-0.25

nor

-0.25

atori

-0.24

itter

-0.24

ator

-0.24

istro

-0.23

åĪĩ

-0.23

ators

-0.23

èĢĮæĺ¯

-0.23

POSITIVE LOGITS

ULER

0.26

awe

0.25

çĶŁæ´»ä¸Ń

0.25

åľ¨çĶŁæ´»ä¸Ń

0.24

ypad

0.24

çŀĳ

0.24

...)

0.24

creen

0.24

å¥ī

0.23

UGH

0.23

Activations Density 0.233%

No Known Activations

This feature has no known activations.