INDEX

Explanations

code and language

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 drive

-0.31

drive

-0.31

Drive

-0.30

 Drive

-0.30

é©±åĬ¨

-0.28

åıĺ

-0.28

onen

-0.28

-drive

-0.27

 Kore

-0.26

éĽĨåĽ¢èĤ¡ä»½

-0.26

POSITIVE LOGITS

ä¸įæŃ»

0.30

Ctr

0.28

igated

0.26

igu

0.26

 META

0.26

 amnesty

0.25

.avi

0.25

_sess

0.24

chrift

0.23

çī¹çĤ¹æĺ¯

0.23

Activations Density 0.015%

code and language

No Comments

No Known Activations