INDEX

Explanations

Citations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æļ´éľ²

-0.31

è°Īè¯Ŀ

-0.27

åĬłåĢį

-0.26

 reflection

-0.25

.Redirect

-0.25

 fÄ±

-0.24

HttpException

-0.24

ä¸Ģåı£

-0.24

ifar

-0.24

çĪ±åĲĥ

-0.24

POSITIVE LOGITS

utters

0.32

studio

0.30

arsers

0.26

æ°´éĿ¢

0.25

 studio

0.25

aters

0.25

meteor

0.24

Pad

0.24

clude

0.24

å¼±

0.24

Activations Density 1.016%

Citations

No Comments

No Known Activations