INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Lay

-0.27

 lique

-0.26

éĨļ

-0.25

zyst

-0.24

Ä±lÄ±

-0.24

phan

-0.24

 genie

-0.24

uese

-0.23

å½ĸ

-0.23

arez

-0.23

POSITIVE LOGITS

itz

0.33

erton

0.29

indi

0.29

ennen

0.27

ber

0.27

ingle

0.26

ç¼º

0.25

ITT

0.25

çłĶç©¶ä¸Ńå¿ĥ

0.24

itt

0.23

Activations Density 0.002%

Code

No Comments

No Known Activations