INDEX

Explanations

news and current events

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

ç»Ļä½ł

-0.26

ä½łçļĦ

-0.26

Tier

-0.26

èĬ±çĵ£

-0.25

å¸ĮæľĽ

-0.25

 Polygon

-0.25

ä¿Ĺ

-0.24

appers

-0.24

actic

-0.24

Polygon

-0.23

POSITIVE LOGITS

rar

0.27

çŃ¾è¯ģ

0.26

 Sears

0.26

ä¸ĩä¸Ģ

0.25

newline

0.25

å¯¹æŃ¤

0.25

ears

0.24

åħ¨åªĴä½ĵ

0.24

æ³³

0.24

rray

0.24

Activations Density 58.842%

news and current events

No Comments

No Known Activations