INDEX

Explanations

stream

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éģįåıĬ

-0.28

éļıæīĭ

-0.27

 Into

-0.26

/by

-0.25

EPS

-0.24

 Income

-0.24

 carefully

-0.24

ä½ıæīĢ

-0.23

tÄ±r

-0.23

å¥½ä¸įå®¹æĺĵ

-0.23

POSITIVE LOGITS

isman

0.29

ä¸Ńæłĩ

0.29

åħµåĽ¢

0.27

æ²īè¿·

0.26

URAL

0.25

çīį

0.25

*</

0.24

 inhibition

0.24

indle

0.24

pref

0.24

Activations Density 4.532%

stream

No Comments

No Known Activations