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

éĥ¨åĪĨ

-0.28

Poss

-0.27

olumn

-0.26

.persist

-0.25

OnInit

-0.24

icable

-0.23

.setColumns

-0.23

odash

-0.23

CharArray

-0.23

[sizeof

-0.23

POSITIVE LOGITS

èĢĮå¯¹äºİ

0.28

 Attr

0.25

éŀŃ

0.25

ê²©

0.25

Ð¸Ð³

0.25

 rented

0.24

juven

0.24

Gul

0.24

inker

0.24

 rental

0.24

Activations Density 0.043%

No Known Activations

This feature has no known activations.