INDEX

Explanations

display

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ide

-0.27

çĽĺçĤ¹

-0.26

isco

-0.25

 martin

-0.25

ç²¾

-0.25

 tying

-0.25

ay

-0.24

 sparkle

-0.24

ingly

-0.24

 mies

-0.23

POSITIVE LOGITS

 oversh

0.26

 UserModel

0.25

nell

0.25

ä¸Ģç«Ļ

0.24

 Governors

0.23

åħĪå¯¼

0.23

 Thornton

0.23

.Elapsed

0.23

Sur

0.23

 Username

0.23

Activations Density 31.061%

display

No Comments

No Known Activations