INDEX

Explanations

presence

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Elections

-0.27

nard

-0.26

 ranks

-0.25

 sleeps

-0.25

uchs

-0.24

à¸²à¸ģ

-0.24

Ø±Ø´

-0.24

 deltas

-0.24

 elections

-0.24

pis

-0.24

POSITIVE LOGITS

 presence

0.35

 present

0.33

 power

0.31

Power

0.30

presence

0.29

 presenÃ§a

0.29

 Power

0.28

 Presence

0.28

ãģĮãĤī

0.28

 Present

0.27

Activations Density 0.019%

presence

No Comments

No Known Activations