INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ANTE

-0.27

ìļķ

-0.26

åĽłä¸ºæĪĳ

-0.25

 Architect

-0.25

 bathtub

-0.25

PostExecute

-0.25

cca

-0.25

å°ıå°ı

-0.24

åĲĥè¿ĩ

-0.24

åĮĸåĲĪ

-0.23

POSITIVE LOGITS

ownt

0.30

ographics

0.26

ictured

0.26

 tail

0.25

xic

0.25

æļĹ

0.25

advisor

0.25

Pixels

0.24

è¡·

0.24

pery

0.24

Activations Density 0.166%

No Known Activations

This feature has no known activations.