INDEX

Explanations

5

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

chief

-0.27

åīĲ

-0.26

åŁĥå°Ķ

-0.26

èĭĭ

-0.25

 chief

-0.24

å¢¨è¥¿åĵ¥

-0.23

æ¹Ķ

-0.23

æµ£

-0.23

 cushion

-0.23

_AV

-0.23

POSITIVE LOGITS

ä¾Ľ

0.32

flight

0.28

 gere

0.25

 flight

0.25

ÑĤÐ¸ÑĢÐ¾Ð²

0.24

ØªØ³Ø¬ÙĬÙĦ

0.24

æĬ½

0.24

 JetBrains

0.24

éĩĳåĪļ

0.24

 Limit

0.23

Activations Density 0.029%

5

No Comments

No Known Activations