INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pir

-0.28

è¿ħ

-0.25

åĳ¼

-0.25

åŁİä¹¡

-0.25

atur

-0.25

kal

-0.24

 natur

-0.24

lok

-0.24

FFF

-0.24

leo

-0.23

POSITIVE LOGITS

rage

0.26

said

0.24

IMD

0.24

éĽªèĬ±

0.24

 Nich

0.24

asive

0.24

CellStyle

0.24

 QIcon

0.23

biased

0.23

imetype

0.23

Activations Density 4.918%

No Known Activations

This feature has no known activations.