INDEX

Explanations

breed

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

olare

-0.29

å¢ĥ

-0.28

tom

-0.27

ä¸ºç©º

-0.26

 empty

-0.26

itory

-0.25

 Empty

-0.25

oku

-0.25

icine

-0.25

 sire

-0.25

POSITIVE LOGITS

èĢģåĮĸ

0.30

ä¸»é¡µ

0.27

 proudly

0.27

åĬĽè¿ĺæĺ¯

0.26

å¹´ä¹ĭä¹ħ

0.26

asty

0.26

æĬ¥ä»ĩ

0.26

åĢį

0.24

èĴº

0.24

 Holder

0.24

Activations Density 0.020%

breed

No Comments

No Known Activations