INDEX

Explanations

international

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 leaked

-0.29

Æ°á»£ng

-0.28

 trium

-0.27

çķ¥

-0.27

á»ĩp

-0.27

(types

-0.25

elix

-0.25

æ¾į

-0.25

ç§Ł

-0.25

RS

-0.24

POSITIVE LOGITS

ä¿Ŀ

0.28

 mÃ¹

0.27

èĤĵ

0.27

ä¸ªå¤ļ

0.25

inders

0.25

|=↵

0.24

aoke

0.24

âĪı

0.24

aise

0.24

çĽĴåŃĲ

0.23

Activations Density 0.788%

international

No Comments

No Known Activations