INDEX

Explanations

functionality and general words

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

ombine

-0.27

 Ð¿Ð¾Ð´Ð¿Ð¸Ñģ

-0.26

 Rookie

-0.26

Compatible

-0.26

chedule

-0.26

 Compatible

-0.25

_COMPAT

-0.25

Boost

-0.24

BI

-0.24

 Welcome

-0.24

POSITIVE LOGITS

ä¹ĭåīįçļĦ

0.27

Ã©ny

0.26

å°±å¼Ģå§ĭ

0.26

æľīçļĦäºº

0.26

çľ¼æ³ª

0.26

 undef

0.26

 ticking

0.25

å°±æľīäºĨ

0.25

å°±å¾Ī

0.25

 rats

0.25

Activations Density 0.003%

functionality and general words

No Comments

No Known Activations