INDEX

Explanations

formal writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Plains

-0.30

strand

-0.26

})(

-0.26

ennes

-0.25

antic

-0.24

èĮ«

-0.24

))^

-0.24

å¥³è£ħ

-0.24

achi

-0.23

relude

-0.23

POSITIVE LOGITS

LEE

0.29

Spe

0.28

Spe

0.27

 horny

0.26

Smy

0.26

ded

0.26

Ð½ÑıÑĤ

0.25

 damn

0.25

 hell

0.24

/gpl

0.24

Activations Density 0.014%

formal writing

No Comments

No Known Activations