INDEX

Explanations

cash

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

 plaque

-0.30

åĬłå¤§å¯¹

-0.25

PointerType

-0.25

çľĭä¸Ģä¸ĭ

-0.24

exual

-0.24

åĬłå¼ºå¯¹

-0.24

æĬĬæīĭ

-0.24

à¸¨

-0.24

 ranged

-0.24

olor

-0.24

POSITIVE LOGITS

ç¦»

0.28

æ¨Ĺ

0.28

bih

0.27

+v

0.26

ìĦ¤

0.25

è¿Ĳ

0.25

åĨ³å®ļ

0.25

èĥ½æ»¡è¶³

0.25

wyn

0.24

è¡Ĺå¤´

0.24

Activations Density 0.814%

cash

No Comments

No Known Activations