INDEX

Explanations

iform and oid

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¿ĿçķĻ

-0.25

Ã£ng

-0.25

amedi

-0.24

mons

-0.24

ahlen

-0.23

utow

-0.23

isma

-0.23

 onion

-0.23

Shock

-0.23

BackColor

-0.22

POSITIVE LOGITS

0.31

pell

0.31

iro

0.30

iros

0.28

å¼¹

0.28

ly

0.28

á»Ń

0.25

Ð¸ÑĨÐµ

0.25

iped

0.25

å±ī

0.25

Activations Density 0.342%

iform and oid

No Comments

No Known Activations