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

è¹ĩ

-0.31

Reuse

-0.27

 dean

-0.26

_until

-0.26

omo

-0.26

ç²Ł

-0.25

æĥ¯

-0.25

çĶŁäºİ

-0.25

ä¸įå°½

-0.25

 ellipt

-0.25

POSITIVE LOGITS

è£ħ

0.28

pled

0.28

-ended

0.26

lijke

0.26

ulis

0.25

 even

0.24

ables

0.24

åį³ä½¿

0.24

lo

0.24

à¹Īà¸ĩ

0.24

Activations Density 0.198%

No Known Activations

This feature has no known activations.