INDEX

Explanations

biology

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 gÃ©n

-0.30

 tune

-0.27

æĮģå¹³

-0.27

èĬ

-0.26

LAY

-0.26

burgh

-0.26

éķ«

-0.25

äº¤åıī

-0.25

ç»ĦæĪĲçļĦ

-0.24

 tied

-0.24

POSITIVE LOGITS

æĹ©ãģĦ

0.26

ecc

0.25

ead

0.25

Ore

0.24

uer

0.24

Wor

0.24

lication

0.24

asic

0.24

ore

0.23

åİŁçĲĨ

0.23

Activations Density 13.875%

biology

No Comments

No Known Activations