INDEX

Explanations

scientific texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_12.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.12.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

falls

-0.30

éĻįæ¸©

-0.30

iesen

-0.28

edef

-0.27

backs

-0.26

iet

-0.25

 Transformer

-0.25

mine

-0.25

çī¹æ®Ĭ

-0.24

èĿī

-0.24

POSITIVE LOGITS

,:,:

0.28

_Frame

0.28

çĶ·åŃ©åŃĲ

0.26

æ¥«

0.26

äºĨå¤ļå°ĳ

0.25

çī©çĲĨåŃ¦

0.25

Mess

0.25

-Fi

0.24

çŃı

0.24

ught

0.24

Activations Density 0.001%

scientific texts

No Comments

No Known Activations