INDEX

Explanations

cigarette

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

éĵĻ

-0.29

wig

-0.28

 panic

-0.28

 componentDid

-0.27

éªŀ

-0.26

orman

-0.26

NEL

-0.25

anim

-0.25

ellan

-0.25

dana

-0.24

POSITIVE LOGITS

_tolerance

0.27

çĽ¸åħ³æĶ¿çŃĸ

0.26

 States

0.26

usch

0.26

([[

0.25

 states

0.25

ä¸ĸçķĮä¸ĬæľĢ

0.25

 deepest

0.25

çŃĶé¢ĺ

0.24

locker

0.24

Activations Density 0.005%

cigarette

No Comments

No Known Activations