INDEX

Explanations

India

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

è¿ĩåİ»

-0.27

ikh

-0.26

çĶŁæŃ»

-0.26

Å»

-0.25

ION

-0.25

,[],

-0.24

 vent

-0.24

inge

-0.24

.element

-0.23

ioned

-0.23

POSITIVE LOGITS

çŃīæĸ¹éĿ¢çļĦ

0.28

eming

0.28

Vul

0.27

 slur

0.27

amel

0.26

 MySql

0.25

åħ¨éĿ¢åıĳå±ķ

0.25

ewise

0.24

 exercise

0.24

pector

0.24

Activations Density 0.001%

India

No Comments

No Known Activations