INDEX

Explanations

Medical conditions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸ĭæĿ¥çļĦ

-0.31

ãģ»ãģĨ

-0.28

æ¯Ķè¾ĥç®Ģåįķ

-0.26

neg

-0.25

ä¸Ńåħ³

-0.25

èĬ

-0.25

RAM

-0.25

 ÑĨÐ¸ÑĦÑĢ

-0.25

neg

-0.25

åľ°ä¸Ĭ

-0.25

POSITIVE LOGITS

sut

0.26

ç¶Ń

0.25

 Buen

0.25

pha

0.25

 Maintain

0.24

 sustained

0.24

well

0.23

éĹ´

0.23

æĻķ

0.23

 Thousand

0.23

Activations Density 0.031%

Medical conditions

No Comments

No Known Activations