INDEX

Explanations

Unorganized data / documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĸ½

-0.28

Ha

-0.28

 known

-0.28

 flying

-0.27

abil

-0.27

 classic

-0.26

ram

-0.26

own

-0.26

-0.25

Aware

-0.25

POSITIVE LOGITS

æĸ¥

0.30

å¹´ä¹ĭ

0.28

ajan

0.26

GMC

0.26

adera

0.26

.SizeF

0.26

çļĦå±ĢéĿ¢

0.25

Scaler

0.25

ISM

0.25

erness

0.24

Activations Density 0.001%

Unorganized data / documents

No Comments

No Known Activations