INDEX

Explanations

News articles/blog posts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 hoping

-0.29

habit

-0.26

åħľ

-0.26

è¯¯å¯¼

-0.26

 trying

-0.25

TRY

-0.25

_nh

-0.25

TRY

-0.25

nod

-0.25

 Trying

-0.25

POSITIVE LOGITS

lot

0.28

lime

0.28

è½®

0.27

lav

0.27

pen

0.26

åĪĽéĢłåĩº

0.26

ibo

0.25

åĪĨå·¥

0.25

ain

0.24

edic

0.24

Activations Density 12.680%

News articles/blog posts

No Comments

No Known Activations