INDEX

Explanations

Pal

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

æķ£

-0.29

 sine

-0.28

sin

-0.28

(sin

-0.27

çª¦

-0.26

zano

-0.26

Ð¸Ð½Ñĭ

-0.25

casts

-0.25

ä¹Łä¸įä¾ĭå¤ĸ

-0.25

Ð¸Ð½Ð°

-0.24

POSITIVE LOGITS

UPPORT

0.28

æĺŁçĲĥ

0.27

çļĦä¹łæĥ¯

0.27

ãģ¾ãģļ

0.26

çĽĶ

0.25

Dh

0.24

ãĥ¼ãĥ³

0.24

gh

0.24

agent

0.24

à¹Īà¸Ńà¸Ļ

0.24

Activations Density 0.004%

Pal

No Comments

No Known Activations