INDEX

Explanations

effective

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

Negative Logits

olated

-0.35

yers

-0.28

acro

-0.27

å°Ŀ

-0.27

 gren

-0.26

 Firm

-0.25

éĨĽ

-0.25

Å¡t

-0.24

.bytes

-0.24

 krÃ³

-0.24

POSITIVE LOGITS

ness

0.43

idad

0.33

NESS

0.29

mente

0.26

 contractual

0.25

zza

0.25

æīĵçĲĥ

0.24

ab

0.24

_runtime

0.23

èĳ£äºĭä¼ļ

0.23

Activations Density 0.178%

effective

No Known Activations