INDEX

Explanations

Medical contexts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultMessage

-0.30

ampa

-0.28

ince

-0.26

ISC

-0.26

artz

-0.26

mars

-0.25

 conditions

-0.24

ä»Ĩ

-0.24

elman

-0.24

ä¸¾æŃ¢

-0.23

POSITIVE LOGITS

á»ģn

0.29

PerPage

0.28

PerPixel

0.28

PagerAdapter

0.27

afs

0.26

.getTag

0.26

TypeID

0.26

 HÃ¶he

0.25

rgb

0.25

å²Ĺ

0.25

Activations Density 0.008%

Medical contexts

No Comments

No Known Activations