INDEX

Explanations

1

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

igrams

-0.29

IMO

-0.28

/tool

-0.27

oblins

-0.25

 masking

-0.25

eland

-0.24

ukan

-0.24

æ¸į

-0.24

å¸ĥé²ģ

-0.24

å²¸

-0.24

POSITIVE LOGITS

çĶµæºĲ

0.34

çĶµåİĭ

0.32

çĶµæ±ł

0.30

 battery

0.29

astype

0.28

çĶµç½ĳ

0.28

lat

0.27

ä¾ĽçĶµ

0.27

éĢļè®¯åĳĺ

0.27

 circuits

0.27

Activations Density 0.002%

1

No Comments

No Known Activations