INDEX

Explanations

Lloyd/Floyd

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

æĻļ

-0.24

_$

-0.24

nofollow

-0.24

Drv

-0.23

zia

-0.23

ussions

-0.23

raz

-0.22

è¿ŀéĶģ

-0.22

otte

-0.22

Aut

-0.22

POSITIVE LOGITS

æŁ½

0.29

æĸ°é²ľ

0.28

æľ¬å¸Ĥ

0.27

xin

0.26

ngle

0.26

 blush

0.25

esis

0.25

 slip

0.24

ç¬¬äºĮç§į

0.24

 specific

0.24

Activations Density 29.370%

Lloyd/Floyd

No Comments

No Known Activations