INDEX

Explanations

Medical/technical document details

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¹´ä»£

-0.34

opsis

-0.27

irty

-0.26

é£¨

-0.26

åľ°æłĩ

-0.25

zie

-0.25

bour

-0.25

æļ§

-0.25

 setC

-0.24

ç«ĸ

-0.24

POSITIVE LOGITS

åĽŃ

0.32

æ¦ľ

0.28

graduate

0.27

æł·

0.26

 catching

0.25

iah

0.24

 volume

0.24

 Aspect

0.24

phan

0.24

ahren

0.24

Activations Density 0.564%

Medical/technical document details

No Comments

No Known Activations