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

åŃĺåľ¨çļĦ

-0.31

 poll

-0.30

Theory

-0.27

Blo

-0.27

 obliged

-0.25

èĹ¤

-0.25

 TASK

-0.25

others

-0.24

elman

-0.24

ers

-0.24

POSITIVE LOGITS

pery

0.28

Yet

0.28

azing

0.27

Yet

0.26

yet

0.26

COME

0.26

åĮħ

0.25

AVIS

0.25

yet

0.25

acity

0.24

Activations Density 0.674%

No Known Activations

This feature has no known activations.