INDEX

Explanations

programming

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

apesh

-0.27

 mest

-0.26

 compulsory

-0.26

çħ§

-0.25

 Arrays

-0.25

åıĺéĩı

-0.25

çĪ¶æ¯į

-0.24

Ã©v

-0.24

 posix

-0.24

åĩ½æķ°

-0.23

POSITIVE LOGITS

 visually

0.36

 graphical

0.35

 visual

0.35

 visualization

0.33

 Interactive

0.33

_visual

0.32

visual

0.32

 Visual

0.30

Visualization

0.29

è®¾è®¡åĻ¨

0.29

Activations Density 39.140%

programming

No Comments

No Known Activations