INDEX

Explanations

code imports

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

å¸ĮæľĽèĩªå·±

-0.26

 Rams

-0.26

eken

-0.26

 firefighter

-0.25

ÐµÐ³

-0.25

-pressure

-0.24

è´¡

-0.24

åİħ

-0.24

bett

-0.24

 inspected

-0.24

POSITIVE LOGITS

Foot

0.30

çķĻä¸ĭ

0.28

æĢ§å¼º

0.27

äºĮçº§

0.26

Configurer

0.25

æĶ¹ç¼ĸ

0.25

æ¶Ł

0.25

uali

0.24

 Americ

0.24

 wohl

0.24

Activations Density 0.029%

code imports

No Comments

No Known Activations