INDEX

Explanations

mind

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hell

-0.29

 dish

-0.28

dish

-0.28

ç±»äº§åĵģ

-0.27

æ¹¿

-0.27

åĪĨè§£

-0.27

+=(

-0.27

iad

-0.26

ç±»

-0.26

ä¹Łæĺ¯ä¸Ģä¸ª

-0.26

POSITIVE LOGITS

scenes

0.30

scene

0.30

 cram

0.30

(Scene

0.29

Snapshot

0.29

 Scenes

0.29

 Snapshot

0.27

(Gravity

0.27

 Mondays

0.27

 scenes

0.26

Activations Density 0.019%

mind

No Comments

No Known Activations