INDEX

Explanations

medical relapses and remissions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¾¾åĪ°

-0.28

å¦ĩå¥³

-0.26

Dig

-0.26

orman

-0.25

odash

-0.25

 ÑģÐ¾Ð±Ð¾Ð¹

-0.25

Dig

-0.24

eler

-0.24

çłĶç©¶åĳĺ

-0.24

éĺµ

-0.24

POSITIVE LOGITS

åı¬åĽŀ

0.28

ellas

0.28

otts

0.26

éĻĲãĤĬ

0.26

OrNull

0.24

è½¦åĨħ

0.24

åĽŀæĿ¥äºĨ

0.24

ï½Ģ

0.24

unya

0.23

ForRow

0.23

Activations Density 0.007%

medical relapses and remissions

No Comments

No Known Activations