INDEX

Explanations

catechol

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

 Statement

-0.27

anza

-0.27

æľºä¼ļ

-0.25

casting

-0.24

cki

-0.24

æ¡Īä¾ĭ

-0.24

åıªæľī

-0.24

 Election

-0.24

 Automatically

-0.23

ä¹Łåıªæľī

-0.23

POSITIVE LOGITS

 Ð¿Ð¾Ð»Ñĥ

0.29

 discipl

0.28

çķĢ

0.28

 disciplined

0.28

ç¼ģ

0.27

IFY

0.26

 discipline

0.26

 colon

0.25

ëĵ¬

0.25

ails

0.24

Activations Density 36.067%

catechol

No Comments

No Known Activations