INDEX

Explanations

accidents and safety

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

ä¸Ńåħ³

-0.28

off

-0.27

tte

-0.26

 transcription

-0.25

 trans

-0.25

èµ°äºĨ

-0.25

Off

-0.24

cription

-0.24

mode

-0.24

-off

-0.24

POSITIVE LOGITS

apters

0.29

authenticated

0.27

è¿Ļåĩłä¸ª

0.27

 ogÃ³le

0.26

 authenticated

0.25

 thÄĥm

0.24

_roles

0.24

oubted

0.24

 Contacts

0.24

 dresser

0.24

Activations Density 0.012%

accidents and safety

No Comments

No Known Activations