INDEX

Explanations

dollar amounts

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

æŃ¢

-0.33

/sources

-0.27

lÃ¢

-0.25

pins

-0.25

ç¨³å®ļæĢ§

-0.25

;br

-0.25

äºļæ´²

-0.25

è¯Ĭ

-0.24

sters

-0.24

çĴĺ

-0.24

POSITIVE LOGITS

romo

0.30

 iota

0.29

ypress

0.27

_ie

0.25

 wonders

0.25

inth

0.25

éķ¿å¤§äºĨ

0.25

-old

0.24

è¿Ļä¸ªè¯į

0.24

 superclass

0.24

Activations Density 0.010%

dollar amounts

No Comments

No Known Activations