INDEX

Explanations

code and numbers

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

åĲįä¹ī

-0.33

Ã¤Ã¤

-0.28

 bÃ¶

-0.26

Ð°Ð¿

-0.25

emain

-0.25

åħ¥åı£

-0.24

CUR

-0.24

 shut

-0.23

å¾Ĵ

-0.23

æ»´

-0.23

POSITIVE LOGITS

ç¬¬ä¸ĢæĿ¡

0.29

assen

0.27

enberg

0.27

ilater

0.26

enburg

0.25

 intra

0.25

ellow

0.25

intern

0.24

otes

0.24

BUG

0.24

Activations Density 0.592%

code and numbers

No Comments

No Known Activations