INDEX

Explanations

code or academic papers

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

æ§İ

-0.32

å¥ĩçº³

-0.27

èļĢ

-0.26

 phÃ¡

-0.26

ä¸įè´Ł

-0.25

ills

-0.25

ç£ĭåķĨ

-0.25

ãĤ³ãĥ¼

-0.25

ioneer

-0.25

ÑĭÑĤÐ°

-0.24

POSITIVE LOGITS

åºı

0.30

 Gener

0.29

ivil

0.28

 gener

0.27

 switch

0.26

/Gate

0.26

olie

0.26

 engine

0.26

 engines

0.25

 switched

0.25

Activations Density 0.014%

code or academic papers

No Comments

No Known Activations