INDEX

Explanations

HE

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æľįåĬ¡å¹³åı°

-0.34

æľīä»·åĢ¼

-0.26

ramento

-0.26

çļĦä¸ĢéĿ¢

-0.26

 Vaults

-0.26

éĻįèĲ½

-0.25

 Millennium

-0.25

æ²Į

-0.25

ç»ģ

-0.24

bindung

-0.24

POSITIVE LOGITS

åĬŁå¤«

0.31

Imp

0.29

imp

0.28

 spider

0.27

hoff

0.26

 polar

0.26

Imp

0.26

èĳ«èĬ¦

0.26

èĻŀ

0.26

Impl

0.25

Activations Density 0.140%

HE

No Comments

No Known Activations