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

èĬ½

-0.33

éķ¿çŁŃ

-0.29

Translations

-0.25

know

-0.25

pll

-0.24

å¥Ī

-0.24

Platforms

-0.24

ouve

-0.24

pll

-0.24

headed

-0.24

POSITIVE LOGITS

ictim

0.29

icas

0.28

raj

0.27

 repairs

0.27

uction

0.26

 ÑĢÐµÐ¼Ð¾Ð½ÑĤ

0.25

 ÑĦÐ¸Ð½

0.25

Ã¸j

0.25

äºĶæĺŁ

0.25

bri

0.25

Activations Density 0.111%

citations

No Comments

No Known Activations