INDEX

Explanations

business context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

opus

-0.27

çļĦå½¢å¼ı

-0.26

å½¢å¼ı

-0.26

ãĥĬãĤ¤

-0.26

=forms

-0.25

 sanct

-0.25

cut

-0.25

ç¼ħ

-0.25

æĿ¥çĶµ

-0.25

 bursts

-0.24

POSITIVE LOGITS

 stayed

0.28

ILLE

0.27

 stay

0.27

pped

0.27

etes

0.26

åĵįåºĶ

0.26

Mi

0.26

çļĦä¸įåĲĮ

0.25

 Holding

0.24

ContextHolder

0.24

Activations Density 0.004%

business context

No Known Activations