INDEX

Explanations

technical and people contexts

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

èĻļ

-0.32

 express

-0.27

å·¥ä¸ļåĮĸ

-0.26

åı¯ä»¥ä½¿

-0.26

 bear

-0.25

åİŁæĸĩåľ°åĿĢ

-0.24

–

-0.24

selectedIndex

-0.24

è±¡

-0.24

Express

-0.24

POSITIVE LOGITS

feit

0.27

åĨ³æĪĺ

0.27

pread

0.26

osci

0.25

oro

0.25

è¿Ļå¥Ĺ

0.25

KIT

0.25

 attention

0.25

FFE

0.24

æĥħæĬ¥

0.24

Activations Density 0.011%

technical and people contexts

No Comments

No Known Activations