INDEX

Explanations

flavor

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nes

-0.30

 Carpenter

-0.29

åŀ£

-0.28

vn

-0.28

hec

-0.26

oning

-0.25

 Apostle

-0.25

éĴİ

-0.25

.getStatusCode

-0.25

å¸ĸåŃĲ

-0.24

POSITIVE LOGITS

WO

0.28

æĪļ

0.26

WF

0.26

 IConfiguration

0.26

configuration

0.25

åº¶

0.25

.lex

0.24

Unsigned

0.24

 quantitative

0.24

éģĦ

0.24

Activations Density 0.062%

flavor

No Comments

No Known Activations