INDEX

Explanations

face

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iced

-0.26

èĮ¶

-0.26

etc

-0.24

kin

-0.23

sense

-0.23

-0.22

akis

-0.22

åĩºäºİ

-0.22

icates

-0.22

è¾ĵ

-0.22

POSITIVE LOGITS

kehr

0.28

ä¸¥å³»

0.28

oire

0.26

 Ð²Ð°Ð¶Ð½Ð¾

0.26

laps

0.25

pekt

0.25

ãĥ¬ãĥ³

0.24

geries

0.24

åĴĦ

0.24

 ÑĥÑģÐ»

0.24

Activations Density 1.151%

face

No Comments

No Known Activations