INDEX

Explanations

delegations

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

çĶ·æĸ¹

-0.31

inha

-0.26

%X

-0.26

æ©Ĳ

-0.26

å¥³æĸ¹

-0.25

rib

-0.25

å®ŀ

-0.24

éķ¯

-0.24

zie

-0.24

unde

-0.24

POSITIVE LOGITS

 indoors

0.31

 lens

0.28

bay

0.27

 rains

0.25

 Lens

0.25

 Newspaper

0.25

RSS

0.24

éķľ

0.24

ä»¥ä¸ĬçļĦ

0.24

 Geography

0.23

Activations Density 0.026%

delegations

No Comments

No Known Activations