INDEX

Explanations

Code and Math

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

/utility

-0.31

 recip

-0.29

expected

-0.28

æľŁæľĽ

-0.28

 expected

-0.27

 expectation

-0.26

_expect

-0.26

Expect

-0.25

ä½Ľæ³ķ

-0.25

 Redistribution

-0.25

POSITIVE LOGITS

 sqrt

0.37

qrt

0.34

sqrt

0.33

.Sqrt

0.32

âĪļ

0.30

.sqrt

0.29

_sqrt

0.28

æĹłè¾ľ

0.27

(sqrt

0.26

overn

0.26

Activations Density 0.014%

Code and Math

No Comments

No Known Activations