INDEX

Explanations

discussions and suggestions

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

:Register

-0.30

éĵ¡

-0.29

igy

-0.27

èİ«æĸ¯

-0.27

ä½¿çĶ¨èĢħæĪĸ

-0.26

anke

-0.26

ITY

-0.25

imate

-0.25

Ranked

-0.24

 medically

-0.24

POSITIVE LOGITS

brid

0.27

Sne

0.26

à¸£à¸²

0.26

éĢļãĤĬ

0.25

capt

0.25

placeholder

0.25

é¥

0.24

 reflections

0.24

 dÃ©p

0.24

ç¤¾ä¼ļåıĳå±ķ

0.24

Activations Density 0.032%

discussions and suggestions

No Comments

No Known Activations