INDEX

Explanations

addition

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

VB

-0.30

 updated

-0.27

éªĢ

-0.26

ZE

-0.25

itecture

-0.24

Lun

-0.23

 recover

-0.23

æľ¬ç«Ļ

-0.23

 MERCHANTABILITY

-0.23

lua

-0.23

POSITIVE LOGITS

edList

0.26

å°ĳè§ģ

0.24

igue

0.23

åĤ¢

0.23

matrix

0.23

ãĤ¢ãĤ¯ãĤ»

0.23

çľģæķĻèĤ²åİħ

0.23

åĽŀåĪ°å®¶

0.23

 Daniels

0.22

 JsonSerializer

0.22

Activations Density 0.004%

addition

No Comments

No Known Activations