INDEX

Explanations

communication and relationships

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

digits

-0.26

ional

-0.26

ob

-0.25

é¦ĸä½į

-0.24

idders

-0.24

å±±åºĦ

-0.23

 issuer

-0.23

åİĨä»£

-0.23

åĳ¨åĽĽ

-0.23

ob

-0.23

POSITIVE LOGITS

 moveTo

0.31

phy

0.26

ä»ĺ

0.25

sequential

0.25

 powering

0.24

_MAT

0.24

elsey

0.24

ä¸ĢçĽ´æ²¡æľī

0.24

æİ§èĤ¡éĽĨåĽ¢

0.23

moved

0.23

Activations Density 0.009%

communication and relationships

No Comments

No Known Activations