INDEX

Explanations

medical

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

èĪįä¸įå¾Ĺ

-0.27

æĥļ

-0.26

åħ¨æĹ¥

-0.25

ToStr

-0.25

stag

-0.24

wap

-0.24

æį©

-0.24

 Plane

-0.24

ä¸ĭåįĬ

-0.23

 opendir

-0.23

POSITIVE LOGITS

itÃ¤t

0.30

 medicine

0.29

mente

0.27

ities

0.27

 Medicine

0.27

idad

0.26

esthesia

0.26

idades

0.26

 trib

0.26

 institutions

0.26

Activations Density 0.063%

medical

No Comments

No Known Activations