INDEX

Explanations

the

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dead

-0.32

-ahead

-0.31

dead

-0.31

adge

-0.30

æıĲ

-0.28

-0.27

 Dead

-0.27

-wise

-0.26

—

-0.26

POSITIVE LOGITS

unh

0.31

parcel

0.30

emes

0.30

 parcel

0.28

 parcels

0.27

onet

0.27

 moden

0.27

rama

0.27

onomies

0.27

ulk

0.26

Activations Density 0.006%

the

No Comments

No Known Activations