INDEX

Explanations

possibility and suggestions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 polled

-0.26

 outstanding

-0.26

 bats

-0.25

åĳĬè¯īå¥¹

-0.25

 attractive

-0.25

å¼

-0.25

åĳĬè¯īå¤§å®¶

-0.24

LOGGER

-0.24

 forwards

-0.24

idders

-0.24

POSITIVE LOGITS

ä¼¼ä¹İ

0.30

thest

0.27

ä¹Ł

0.26

INCT

0.26

 Licence

0.25

çĶŁ

0.25

noun

0.25

lish

0.24

éħ¿

0.24

Activations Density 0.008%

possibility and suggestions

No Comments

No Known Activations