INDEX

Explanations

Racing teams

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

leased

-0.30

 Ð¿ÑĢÐ°Ð·

-0.27

StorageSync

-0.27

 Hayward

-0.26

hashed

-0.25

å±ķåĵģ

-0.25

åĪ·

-0.25

æ¦´

-0.24

 znal

-0.24

apsed

-0.24

POSITIVE LOGITS

èĬĿ

0.32

ä»ĭ

0.28

witch

0.28

uling

0.27

erior

0.27

Tu

0.26

unan

0.26

eon

0.25

 Tape

0.25

BT

0.24

Activations Density 0.086%

Racing teams

No Comments

No Known Activations