INDEX

Explanations

programming code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

Ð¸Ð½Ð´

-0.26

 Abuse

-0.26

 Banc

-0.25

èĭ¥æĤ¨

-0.25

è¯·æĤ¨

-0.24

irty

-0.24

 compact

-0.24

;q

-0.24

æĤ¨çļĦåŃ©åŃĲ

-0.24

è§ģè¯ģ

-0.24

POSITIVE LOGITS

å·¡

0.28

ç¨¿

0.27

|--

0.27

NG

0.26

↵

0.25

 č↵

0.25

ä¹¦ä¸Ń

0.25

XI

0.24

č↵

0.24

plane

0.24

Activations Density 0.004%

programming code

No Comments

No Known Activations