INDEX

Explanations

Units of measurement

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

Phase

-0.29

ched

-0.28

OMIC

-0.25

 Phase

-0.25

 phase

-0.24

æŃ£ç¡®

-0.24

ely

-0.24

fv

-0.24

DESC

-0.24

Record

-0.24

POSITIVE LOGITS

åħĪè¡Į

0.32

 wast

0.26

amina

0.26

abras

0.26

åķ¬

0.26

 modifiers

0.25

olon

0.24

æĻĴ

0.24

 mathematics

0.23

 currency

0.23

Activations Density 0.003%

Units of measurement

No Comments

No Known Activations