INDEX

Explanations

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

 purpose

-0.27

geh

-0.27

ISCO

-0.26

çļĦçĽ®çļĦ

-0.26

_organization

-0.26

kas

-0.25

organization

-0.25

à¸Ĩ

-0.24

 Purpose

-0.24

ernal

-0.24

POSITIVE LOGITS

 sings

0.25

çĥ

0.25

çŃĸ

0.25

å¼Ģæľº

0.25

ä¸ĵé¡¹è¡ĮåĬ¨

0.24

å£°ç§°

0.23

åıĳåĩº

0.23

éĻĲéĩı

0.23

 cand

0.23

å©ļåĲİ

0.23

Activations Density 7.209%

code

No Comments

No Known Activations