INDEX

Explanations

Indicating time or sequence

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

-0.27

æīĵ

-0.26

_.

-0.26

 genu

-0.25

 Comb

-0.25

åĲī

-0.25

éĺ²çĸ«

-0.25

 couple

-0.25

analy

-0.24

POSITIVE LOGITS

etsk

0.29

.tel

0.28

oire

0.26

lessly

0.25

eced

0.25

è¿ĻäºĽéĹ®é¢ĺ

0.24

åħĭæĸ¯

0.24

bugs

0.24

.ls

0.24

æ¯ĽçĹħ

0.24

Activations Density 28.507%

Indicating time or sequence

No Comments

No Known Activations