INDEX

Explanations

2

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

“

-0.29

-che

-0.28

 conf

-0.27

orado

-0.24

 beats

-0.24

é¦Ļ

-0.24

-Americ

-0.24

edx

-0.24

-conf

-0.24

 beat

-0.24

POSITIVE LOGITS

SIG

0.27

æĹ¶åĢĻ

0.25

éĺī

0.25

 Reviewed

0.25

ç½ĳåıĭè¯Ħè®º

0.24

ä¸ĢæĬ¹

0.23

Sig

0.23

à¸³

0.23

lw

0.23

"))

0.23

Activations Density 2.884%

2

No Comments

No Known Activations