INDEX

Explanations

skills, learning, training

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

 slowly

-0.31

 Johnson

-0.25

.Autowired

-0.25

æŃ£

-0.24

æ³¾

-0.24

çłĮ

-0.24

éĢĲæ¸Ĳ

-0.24

 tailor

-0.24

.tie

-0.24

ĵ

-0.24

POSITIVE LOGITS

æ°¾

0.29

éĥ¾

0.28

Cancellation

0.27

 yourselves

0.26

åķ®

0.25

èµĲ

0.25

ilos

0.25

iness

0.25

heten

0.24

				↵				↵

0.24

Activations Density 0.001%

skills, learning, training

No Comments

No Known Activations