INDEX

Explanations

Montreal

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

olve

-0.26

 cran

-0.26

ARA

-0.26

 onViewCreated

-0.25

åĬŀ

-0.24

åĪĳ

-0.23

 ÑĢÐµÑĪÐ¸

-0.23

èĪ¹

-0.23

itz

-0.23

ieten

-0.23

POSITIVE LOGITS

assed

0.30

è¿Ļå¼ł

0.28

odule

0.27

 Euros

0.27

$k

0.25

encies

0.25

ordes

0.25

æĪĳçļĦå¿ĥ

0.25

elm

0.24

ãĥ¼ãĤº

0.24

Activations Density 0.085%

Montreal

No Comments

No Known Activations