INDEX

Explanations

present participles

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

utures

-0.29

jÄĻ

-0.28

èĢĮå·²

-0.27

urat

-0.25

 Explicit

-0.24

 Trades

-0.24

.extra

-0.24

iske

-0.24

 States

-0.24

uries

-0.24

POSITIVE LOGITS

æł·

0.31

Pattern

0.29

ater

0.28

éĢ»è¾ĳ

0.28

¦Ĥ

0.28

 Pill

0.27

_logic

0.27

éĻ¤

0.26

adar

0.26

 Pattern

0.26

Activations Density 0.022%

present participles

No Comments

No Known Activations