INDEX

Explanations

Programming questions/code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Courts

-0.27

olland

-0.26

åĥĸ

-0.25

.mit

-0.24

ailing

-0.24

 Clement

-0.24

åĩ¶

-0.24

 carÃ¡cter

-0.24

older

-0.24

 trouble

-0.24

POSITIVE LOGITS

ubo

0.28

 undo

0.28

awn

0.27

packageName

0.26

setContent

0.26

è¿ģç§»

0.25

æ·¹

0.25

 reset

0.25

_UD

0.25

åľ°éľĩ

0.25

Activations Density 0.234%

Programming questions/code

No Comments

No Known Activations