INDEX

Explanations

cross

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĹ¢çĦ¶

-0.30

èº«ç©¿

-0.28

éŁŃ

-0.27

iber

-0.25

amil

-0.25

æĺ¯éĿŀ

-0.25

 compartment

-0.24

 vows

-0.24

åİŁæĿ¥æĺ¯

-0.24

 mutate

-0.23

POSITIVE LOGITS

wiki

0.27

æŃĮ

0.26

kt

0.25

Ð´Ð°Ð»

0.25

Æł

0.25

Town

0.24

kat

0.24

 wiki

0.24

 Town

0.24

seed

0.24

Activations Density 0.809%

cross

No Comments

No Known Activations