INDEX

Explanations

in

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

LF

-0.28

 mass

-0.27

ambique

-0.25

mass

-0.25

 besides

-0.25

çļĦè¶ĭåĬ¿

-0.24

sep

-0.24

æĭĴ

-0.24

ÃŃd

-0.24

 RepÃºblica

-0.24

POSITIVE LOGITS

áº¡c

0.28

(records

0.25

åĲİèĢħ

0.25

Ã©sz

0.25

/sm

0.24

 records

0.24

 RECORD

0.24

.ga

0.24

izzes

0.23

 appName

0.23

Activations Density 0.006%

in

No Comments

No Known Activations