INDEX

Explanations

technical reports

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 computed

-0.29

æĦıå¤§

-0.28

é¸³

-0.27

MARY

-0.27

nge

-0.26

 commuting

-0.26

_ng

-0.25

 hostel

-0.25

ugal

-0.25

computed

-0.24

POSITIVE LOGITS

æº±

0.29

æľ½

0.26

é¢ĸ

0.25

 Heavenly

0.24

æľºåĻ¨

0.24

_HT

0.24

Ã¢n

0.24

-bottom

0.24

 bottoms

0.23

åħ¨æĸĩ

0.23

Activations Density 0.002%

technical reports

No Comments

No Known Activations