INDEX

Explanations

am

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sublic

-0.29

ç»´æĬ¤

-0.26

PTR

-0.26

.activ

-0.25

æīįå¹²

-0.25

@Controller

-0.24

IRST

-0.24

éĤ£åıª

-0.24

pons

-0.23

ä¼ĺéĢī

-0.23

POSITIVE LOGITS

éģĹ

0.30

rev

0.28

rev

0.27

eld

0.26

ë¦½

0.25

 percentile

0.25

asti

0.25

eng

0.25

ç±»åŀĭ

0.25

 sight

0.24

Activations Density 0.001%

am

No Comments

No Known Activations