INDEX

Explanations

Code/Website Text

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

rael

-0.28

 cent

-0.27

Moment

-0.27

éĵ

-0.25

nep

-0.25

ç³¯ç±³

-0.25

azel

-0.25

Ð±Ð¾

-0.25

mom

-0.25

 stoi

-0.25

POSITIVE LOGITS

ç¬Ķ

0.29

ÑģÐ°Ð´

0.25

ertools

0.24

 curly

0.24

 kurs

0.23

pen

0.23

 decreases

0.23

 increases

0.23

éĺ³

0.23

é¸²

0.23

Activations Density 0.001%

Code/Website Text

No Comments

No Known Activations