INDEX

Explanations

math/programming context

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

bett

-0.30

asures

-0.28

IMAL

-0.26

_seqs

-0.25

ollo

-0.24

islation

-0.24

abies

-0.24

 nÃ¤mlich

-0.24

 yourselves

-0.24

::-

-0.24

POSITIVE LOGITS

lib

0.30

 SetProperty

0.29

lib

0.27

æľº

0.27

xi

0.26

éĻĦä»¶

0.26

apper

0.25

çģµæ°Ķ

0.24

ced

0.24

 starting

0.24

Activations Density 0.016%

math/programming context

No Comments

No Known Activations