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

 Conv

-0.28

çķľ

-0.27

åºĦ

-0.27

èİĬ

-0.27

eteor

-0.26

Ignoring

-0.26

Conv

-0.26

ooting

-0.25

æ»Ĥ

-0.25

 Upper

-0.24

POSITIVE LOGITS

çĻŀ

0.26

çļĦåģļæ³ķ

0.26

OPS

0.26

åľ°ä¸Ń

0.25

éĢĢ

0.24

Ð³Ð°Ð´

0.24

.ecore

0.24

cala

0.23

.getError

0.23

.cal

0.23

Activations Density 0.023%

No Known Activations

This feature has no known activations.