INDEX

Explanations

z

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

 distinct

-0.27

áŀĦ

-0.26

distinct

-0.24

åĲĮæĦı

-0.24

_GPU

-0.24

æ¶²

-0.24

åĪ°æĹ¶åĢĻ

-0.24

ped

-0.23

ons

-0.23

èĪĶ

-0.23

POSITIVE LOGITS

åħĳçİ°

0.28

éĴĵ

0.26

emean

0.26

APPLE

0.25

ï¼ļ%

0.25

resher

0.25

dsa

0.24

 Fritz

0.24

PTR

0.24

usses

0.24

Activations Density 0.002%

z

No Comments

No Known Activations