INDEX

Explanations

)

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

hani

-0.29

ption

-0.26

gig

-0.26

 anyway

-0.25

gatsby

-0.24

ä¸ŃéĢĶ

-0.24

 mÅ©i

-0.24

hap

-0.24

á»ĩp

-0.23

roduction

-0.23

POSITIVE LOGITS

çļĦæĥħç»ª

0.26

iteDatabase

0.24

æģ»

0.24

ç«ĭæĸ¹

0.24

åħ¨éĿ¢æİ¨è¿Ľ

0.24

ervlet

0.24

æ³ķå®Ŀ

0.24

 HACK

0.23

 vite

0.23

æķĪåºĶ

0.23

Activations Density 0.161%

)

No Comments

No Known Activations