INDEX

Explanations

common English words

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

ont

-0.32

 Locator

-0.28

BX

-0.28

ponents

-0.27

çĮĿ

-0.27

 Rocket

-0.26

æ¥Ķ

-0.26

Locator

-0.25

catch

-0.25

å¥ĳ

-0.25

POSITIVE LOGITS

irim

0.28

icularly

0.27

endsWith

0.26

ä»ĸä»¬æĺ¯

0.25

witter

0.25

icense

0.25

icolor

0.24

iations

0.24

çĸ¹

0.24

æĶ¾è¿ĩ

0.23

Activations Density 0.917%

common English words

No Comments

No Known Activations