INDEX

Explanations

Memberships and subscriptions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_12.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.12.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

emie

-0.28

specs

-0.27

éĹ³

-0.26

 seals

-0.25

ystone

-0.25

å¼łè´´

-0.25

anium

-0.24

ä¸»æĹ¨

-0.24

oji

-0.24

æŀ¶

-0.24

POSITIVE LOGITS

jer

0.28

åı¯ä»¥éĢīæĭ©

0.28

 participants

0.26

 participant

0.25

ç©¿

0.25

åıĤä¸İèĢħ

0.25

bcd

0.24

åĪĨæľŁ

0.24

ãĥ¡ãĥ³

0.24

odo

0.24

Activations Density 0.002%

Memberships and subscriptions

No Comments

No Known Activations