INDEX

Explanations

to

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

å®¶ä¸Ń

-0.30

 Chancellor

-0.27

")->

-0.27

çľ¼ä¸Ń

-0.26

äº²çľ¼

-0.25

å¿ĥä¸ŃçļĦ

-0.25

GetInstance

-0.25

kaar

-0.24

anta

-0.24

å¼łå®¶

-0.24

POSITIVE LOGITS

 swing

0.27

çĪ±

0.25

 dissip

0.25

Pub

0.24

DJ

0.24

 Phantom

0.24

nehmer

0.24

ard

0.24

nom

0.23

 Tight

0.23

Activations Density 0.079%

to

No Comments

No Known Activations