INDEX

Explanations

of

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dÃ©cid

-0.25

 Chancellor

-0.25

*'

-0.24

æĿĮ

-0.24

eliness

-0.23

 tamil

-0.23

_maker

-0.23

 ordinarily

-0.23

 wann

-0.23

 initialise

-0.23

POSITIVE LOGITS

 Vega

0.26

 distract

0.26

pit

0.25

cia

0.25

pat

0.24

illet

0.24

éĩĩ

0.24

 cata

0.24

/wiki

0.24

ilent

0.23

Activations Density 0.416%

of

No Comments

No Known Activations