INDEX

Explanations

States

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¼¹

-0.27

mou

-0.25

ä¹ī

-0.25

estar

-0.25

åįı

-0.24

tou

-0.24

warf

-0.24

æŃĮèĪŀ

-0.24

][:

-0.24

oine

-0.24

POSITIVE LOGITS

pto

0.30

åķĨåĬ¡éĥ¨

0.27

ŀæĢ§

0.26

ages

0.25

kÃ¼

0.25

allest

0.25

uarios

0.25

isses

0.25

icens

0.24

 Shadows

0.24

Activations Density 0.204%

States

No Comments

No Known Activations