INDEX

Explanations

programming/technical context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĲįçīĩ

-0.27

æĤ²

-0.25

ices

-0.24

viso

-0.24

foil

-0.24

 RATE

-0.24

æ·Į

-0.24

Ã¥n

-0.24

 DISTRIBUT

-0.23

íı¼

-0.23

POSITIVE LOGITS

æ±ģ

0.28

è£Ļ

0.28

 quick

0.27

/py

0.27

quick

0.26

 Hospital

0.25

-haspopup

0.25

landers

0.25

 phÃ¡t

0.24

uito

0.24

Activations Density 0.001%

programming/technical context

No Comments

No Known Activations