INDEX

Explanations

technical writing

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

 Ambient

-0.28

mvc

-0.28

Ð·Ð°Ð¼

-0.27

udded

-0.26

ahir

-0.25

 recap

-0.25

åĮĸåĲĪ

-0.25

 ambient

-0.25

æľīå¤§éĩıçļĦ

-0.24

edList

-0.24

POSITIVE LOGITS

-rel

0.28

coat

0.27

rel

0.27

ly

0.27

 relief

0.26

Rel

0.25

ìĹŃ

0.25

PAGE

0.25

 lending

0.24

rel

0.24

Activations Density 0.038%

technical writing

No Comments

No Known Activations