INDEX

Explanations

research reports

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

éĽ¨

-0.28

 vent

-0.28

éĺĶ

-0.27

 mushroom

-0.27

 dime

-0.26

åĦĴ

-0.25

ream

-0.25

DRV

-0.24

è¯ĹæĦı

-0.24

æ±Ĺ

-0.24

POSITIVE LOGITS

aggio

0.28

å¯¹æĸ¹

0.27

resco

0.26

cestor

0.25

uido

0.25

lse

0.25

å¼ķãģ£

0.24

logue

0.24

æİ©çĽĸ

0.24

åıĮæĸ¹

0.24

Activations Density 3.991%

research reports

No Comments

No Known Activations