INDEX

Explanations

include

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

mith

-0.28

ä¸Ģæĸ¹

-0.28

Virtual

-0.27

å¼¯

-0.24

isp

-0.24

 skips

-0.24

omal

-0.23

VRT

-0.23

æİ©

-0.23

 tráº£i

-0.23

POSITIVE LOGITS

 voluntary

0.27

.HttpServlet

0.26

Vol

0.26

 decom

0.26

getInstance

0.25

 voluntarily

0.24

Vol

0.24

ç´Ĳ

0.24

ric

0.24

-auto

0.24

Activations Density 0.002%

include

No Comments

No Known Activations