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

çļĦæķ°éĩı

-0.27

æľĢåĲİä¸Ģæ¬¡

-0.26

ç²¾

-0.26

åĢŁçĶ¨

-0.25

ãĤ¯ãĥĪ

-0.24

liers

-0.24

 sant

-0.23

ãģĳãģ°

-0.23

uen

-0.23

ItemCount

-0.23

POSITIVE LOGITS

 Lines

0.26

 grids

0.26

 Line

0.26

å¤§å®¶åĪĨäº«

0.25

 Biggest

0.24

 lines

0.23

åĵĨ

0.23

AtIndex

0.23

AGR

0.23

ç§ģ

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.