INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

åĩ«

-0.29

holm

-0.26

laps

-0.24

 Akron

-0.24

POCH

-0.24

 undefeated

-0.24

aunch

-0.23

ç»ıéªĮåĴĮ

-0.23

ernals

-0.23

æ¹

-0.23

POSITIVE LOGITS

åºľ

0.30

ibe

0.26

Gov

0.25

don

0.25

orne

0.24

Gov

0.24

å¤Ħæĸ¹

0.24

ëĮĵ

0.24

å¤·

0.24

arians

0.23

Activations Density 1.871%

No Known Activations

This feature has no known activations.