INDEX

Explanations

libraries and information access

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

å¾ĹåĪĨ

-0.31

æıĴ

-0.29

å®¶

-0.27

å¿Ļç¢Į

-0.25

rette

-0.25

amat

-0.25

 ease

-0.25

èįī

-0.25

è¯Ŀ

-0.25

å¿Ļ

-0.25

POSITIVE LOGITS

 Faculty

0.30

Faculty

0.28

 indexed

0.28

PubMed

0.27

 faculty

0.27

æīĭæĦŁ

0.27

Indented

0.26

faculty

0.25

éļıæīĭ

0.25

 libros

0.25

Activations Density 0.003%

libraries and information access

No Comments

No Known Activations