INDEX

Explanations

organizations

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

æıĲä¾ĽæĽ´å¤ļ

-0.28

 JScrollPane

-0.26

orus

-0.26

 Common

-0.25

omap

-0.25

.chars

-0.25

anked

-0.25

 educated

-0.24

READY

-0.24

èµĽåĮº

-0.24

POSITIVE LOGITS

eve

0.30

inde

0.30

rogen

0.27

åıįå¼¹

0.27

imens

0.26

vana

0.25

comb

0.25

inds

0.25

agini

0.25

 inde

0.24

Activations Density 0.001%

organizations

No Comments

No Known Activations