INDEX

Explanations

Movement or changes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Left

-0.27

åĩºèĩª

-0.27

ushman

-0.25

Left

-0.25

.attach

-0.24

æĿ¥èĩª

-0.24

 Right

-0.24

 left

-0.23

achen

-0.23

left

-0.23

POSITIVE LOGITS

rips

0.31

 momentarily

0.28

éĢļè¡Į

0.27

ynes

0.27

åĩºè®©

0.27

åĪ·

0.26

ilage

0.26

 discussions

0.26

hands

0.26

æĸ¤

0.26

Activations Density 0.001%

Movement or changes

No Comments

No Known Activations