INDEX

Explanations

and

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

è«¸

-0.25

Ð¾ÑĩÐµÐº

-0.24

çºµåĲĳ

-0.23

licate

-0.23

itches

-0.23

ieurs

-0.23

pherd

-0.23

 unlaw

-0.23

dle

-0.23

åįģåĪĨéĩįè¦ģ

-0.22

POSITIVE LOGITS

 interests

0.31

aj

0.29

è§ĤçĤ¹

0.28

 expectations

0.28

beh

0.28

æĥ³æ³ķ

0.26

çķĶ

0.26

æģ©

0.26

 thought

0.26

Activations Density 0.004%

and

No Comments

No Known Activations