INDEX

Explanations

Publish

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

peare

-0.28

NF

-0.26

bff

-0.26

xDE

-0.24

åİī

-0.24

 genuinely

-0.24

nu

-0.23

ALSE

-0.23

NF

-0.23

iro

-0.23

POSITIVE LOGITS

 erot

0.29

gew

0.28

æ°§

0.27

è¿·

0.26

spo

0.26

AtIndex

0.25

æĴĴ

0.25

bject

0.24

.boolean

0.24

arness

0.24

Activations Density 0.017%

Publish

No Comments

No Known Activations