INDEX

Explanations

medical publications

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å®¢

-0.30

jection

-0.27

è·³

-0.27

éĦĻ

-0.26

trak

-0.26

 qualifier

-0.26

åĨ³å®ļäºĨ

-0.26

éĽĢ

-0.25

å¸¸

-0.25

é¥°

-0.24

POSITIVE LOGITS

ivet

0.27

 Orth

0.25

 Minutes

0.25

éĢĻéº¼

0.24

 spawns

0.24

è¦Ĩ

0.24

unders

0.23

needs

0.23

 arous

0.23

usch

0.23

Activations Density 0.008%

medical publications

No Comments

No Known Activations