INDEX

Explanations

than

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 respons

-0.29

åĵĢ

-0.27

çļĦè´£ä»»

-0.25

åī§ä¸Ń

-0.25

 Instit

-0.24

è´£ä»»

-0.24

iten

-0.24

 cour

-0.24

 evolving

-0.24

IQ

-0.24

POSITIVE LOGITS

ç±»ä¼¼çļĦ

0.28

measure

0.26

GetProperty

0.26

orris

0.26

dde

0.26

depends

0.25

 measure

0.25

.GetProperty

0.25

åħ¥å¢ĥ

0.25

åĴĮå¹³

0.25

Activations Density 0.006%

than

No Comments

No Known Activations