INDEX

Explanations

adverbs of degree

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 trotz

-0.30

Cd

-0.26

æĤ£ä¸Ĭ

-0.25

å¦ĤæľŁ

-0.25

è®«

-0.24

eur

-0.24

.GetKey

-0.24

Verb

-0.24

 impost

-0.23

ossa

-0.23

POSITIVE LOGITS

itionally

0.30

éĴĪå¯¹æĢ§

0.29

ŀæĢ§

0.28

 hierarchical

0.27

ically

0.27

 communal

0.26

ä¸Ģçº§

0.26

çļĩåŃĲ

0.26

æ¨ªåĲĳ

0.26

è¯Ī

0.25

Activations Density 0.966%

adverbs of degree

No Comments

No Known Activations