INDEX

Explanations

MBA

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

egie

-0.28

stants

-0.28

 unmarried

-0.27

åįķèº«

-0.26

.enumer

-0.25

å¼ĢæĿ¥

-0.24

 pinch

-0.24

åįı

-0.24

 Parenthood

-0.24

éļ¾åħ³

-0.24

POSITIVE LOGITS

 payer

0.27

æ²®

0.26

MATRIX

0.24

vÃŃ

0.24

 production

0.24

éĥ¨èĲ½

0.24

emento

0.23

Concurrency

0.23

vro

0.23

prod

0.23

Activations Density 15.471%

MBA

No Comments

No Known Activations