INDEX

Explanations

of

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

unce

-0.28

 Cumberland

-0.26

èģ·

-0.25

beg

-0.25

 underline

-0.25

 Ã¶zelliÄŁi

-0.24

ndo

-0.24

mor

-0.24

éģĤ

-0.23

lon

-0.23

POSITIVE LOGITS

sticks

0.27

loh

0.27

ªĮ

0.26

rowsers

0.26

å¤´èĦĳ

0.25

<Select

0.25

AdminController

0.24

æªĶ

0.24

frames

0.24

shots

0.24

Activations Density 0.002%

of

No Comments

No Known Activations