INDEX

Explanations

Code and legal text

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

 Barber

-0.27

åı·

-0.27

 Tall

-0.26

opyright

-0.26

 negativity

-0.26

 borrowing

-0.26

vak

-0.26

RING

-0.26

 rebounds

-0.25

liches

-0.25

POSITIVE LOGITS

strom

0.30

nev

0.29

æĥħ

0.28

igm

0.28

0.27

------------------------------------------------------------------------------------------------

0.27

 spectrum

0.26

č↵↵

0.26

intage

0.26

(:,:,

0.24

Activations Density 0.023%

Code and legal text

No Comments

No Known Activations