INDEX

Explanations

Names and heritage

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

èĬĤèĥ½çİ¯ä¿Ŀ

-0.29

æ¹¾

-0.26

ä¸»èĲ¥

-0.26

åįĳ

-0.25

'gc

-0.25

sha

-0.24

åĪĨæĺİ

-0.23

æµģéĢļ

-0.23

ondo

-0.23

 compt

-0.23

POSITIVE LOGITS

æĸ¥

0.30

ialis

0.28

airy

0.26

 (*((

0.26

 quem

0.26

addError

0.25

(Db

0.25

emento

0.24

quette

0.24

ursor

0.24

Activations Density 0.002%

Names and heritage

No Comments

No Known Activations