INDEX

Explanations

forum posts

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

çŃ

-0.27

æ®ĸ

-0.26

 destin

-0.26

è´ŀ

-0.26

ramid

-0.26

>Delete

-0.25

æĭ©

-0.25

AsyncResult

-0.25

antar

-0.25

_ask

-0.25

POSITIVE LOGITS

ey

0.29

ä¹ĸä¹ĸ

0.29

 Position

0.27

clipse

0.27

 Positioned

0.27

egov

0.27

 turning

0.26

äºĮçº¿åŁİå¸Ĥ

0.26

-turn

0.26

elli

0.25

Activations Density 0.817%

forum posts

No Comments

No Known Activations