INDEX

Explanations

collection

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

èģĶæĥ³

-0.25

 neph

-0.25

æĥ³èµ·

-0.24

éĽĨå¸Ĥ

-0.24

 Incident

-0.24

äººå£«

-0.23

relude

-0.23

URT

-0.23

éħĴä¸ļ

-0.23

leshoot

-0.23

POSITIVE LOGITS

enet

0.31

æĶ¶çº³

0.27

åŁ

0.26

growth

0.25

æľĢç¾İ

0.25

éĥ½æľīèĩªå·±

0.25

çĻ¾å¹´

0.25

 neatly

0.24

 cleanly

0.24

/latest

0.24

Activations Density 0.014%

collection

No Comments

No Known Activations