INDEX

Explanations

of

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

criptor

-0.28

 siblings

-0.28

FAR

-0.27

-edge

-0.27

 sibling

-0.27

 separation

-0.26

IsRequired

-0.26

è¾¹ç¼ĺ

-0.25

ette

-0.25

tax

-0.25

POSITIVE LOGITS

èĥ½å¤Łåľ¨

0.26

ickle

0.26

 táº¯c

0.26

ÃŃch

0.26

 conf

0.26

ç§ĺ

0.25

æ¦Ĩ

0.25

ä»·éĴ±

0.24

æĹı

0.24

IK

0.24

Activations Density 0.012%

of

No Comments

No Known Activations