INDEX

Explanations

Relating to personal experiences

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

oso

-0.26

igor

-0.26

 disturbances

-0.26

atten

-0.26

æĸ°åĮº

-0.25

çī¹æ®Ĭ

-0.25

 oracle

-0.25

ocup

-0.25

èĢ½è¯¯

-0.25

çĲĥ

-0.25

POSITIVE LOGITS

xon

0.32

º«

0.31

 whichever

0.30

fit

0.27

 whatever

0.26

inality

0.25

.Matchers

0.24

 wherever

0.24

 fits

0.24

 conco

0.24

Activations Density 0.003%

Relating to personal experiences

No Comments

No Known Activations