INDEX

Explanations

Code, technical documentation

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

 Ð´Ð°Ð»ÑĮÐ½

-0.26

uits

-0.26

_redirect

-0.25

å±ŀäºİ

-0.25

åħ»

-0.25

å¥¹æĺ¯

-0.24

.dispose

-0.24

éĹŃ

-0.24

RTC

-0.24

ä¸ĭä¸ĢæŃ¥

-0.24

POSITIVE LOGITS

íĨł

0.24

.Maximum

0.24

isten

0.24

 trava

0.24

 defaultProps

0.24

efault

0.24

 fran

0.23

aptop

0.23

 accessibility

0.23

çķ¿

0.23

Activations Density 0.001%

Code, technical documentation

No Comments

No Known Activations