INDEX

Explanations

science

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸Ńå¿ĥ

-0.30

loc

-0.28

sher

-0.26

æĭĨ

-0.26

çłŃ

-0.26

ç²¢

-0.26

loc

-0.25

axed

-0.25

ç¡®

-0.25

ents

-0.25

POSITIVE LOGITS

PRI

0.28

_roll

0.27

_aw

0.27

çĦķåıĳ

0.27

ibbon

0.25

ByPrimaryKey

0.25

åĸĶ

0.25

 unlike

0.24

PRI

0.24

ky

0.24

Activations Density 0.003%

science

No Comments

No Known Activations