INDEX

Explanations

Program

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.39

urbation

-0.25

pay

-0.25

hiba

-0.24

_website

-0.24

ier

-0.24

LEX

-0.24

Ð²Ð¸

-0.24

acin

-0.24

çŃīåĢĻ

-0.23

POSITIVE LOGITS

 Program

0.39

 programs

0.38

 program

0.35

Program

0.35

 Programs

0.33

programs

0.32

program

0.31

 PROGRAM

0.31

 Programme

0.31

 programas

0.31

Activations Density 0.907%

Program

No Comments

No Known Activations