INDEX

Explanations

Math/scientific notation

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

-cond

-0.27

ivel

-0.27

regation

-0.27

èĲ½åĪ°

-0.26

lagen

-0.26

lement

-0.26

 NDEBUG

-0.25

izione

-0.25

èĲ½åľ°

-0.25

qualification

-0.24

POSITIVE LOGITS

æİ¢

0.28

.ke

0.27

æ´

0.27

ULE

0.26

ableObject

0.26

ä¹ĭå£°

0.26

 Flame

0.25

_sa

0.25

 Generated

0.25

åŁł

0.25

Activations Density 0.025%

Math/scientific notation

No Comments

No Known Activations