INDEX

Explanations

programming

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

ëłµ

-0.27

aff

-0.25

 aspiring

-0.25

=ax

-0.25

_SHARED

-0.24

ENCY

-0.24

 hiá»ĩp

-0.24

æĮ¤

-0.24

perimental

-0.24

 pref

-0.23

POSITIVE LOGITS

å®¤

0.27

 copies

0.26

.mac

0.26

çºµæ¨ª

0.26

 Macron

0.25

 copy

0.25

åĽ½éĺ²

0.25

Ã©tÃ©

0.25

åĨ»ç»ĵ

0.24

copies

0.24

Activations Density 0.054%

programming

No Comments

No Known Activations