INDEX

Explanations

CP

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

@g

-0.27

uous

-0.26

ÑĭÐ¼

-0.26

å®³

-0.25

arrison

-0.24

mg

-0.24

ccount

-0.24

æĪĲåĬŁçļĦ

-0.23

 Compar

-0.23

 silently

-0.23

POSITIVE LOGITS

=ax

0.26

schlÃ¤

0.26

-Jul

0.24

lify

0.24

uppen

0.24

adders

0.23

çīµ

0.23

æĬ½æŁ¥

0.23

å¼±çĤ¹

0.23

signals

0.23

Activations Density 5.317%

CP

No Comments

No Known Activations