INDEX

Explanations

crack

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 professionnel

-0.26

Cum

-0.26

ird

-0.26

æİ¨è¿Ł

-0.25

aille

-0.25

_cum

-0.25

Cum

-0.25

perator

-0.24

ource

-0.24

Rug

-0.23

POSITIVE LOGITS

land

0.27

ref

0.26

lated

0.26

è°ľ

0.25

ref

0.25

Box

0.25

 skulls

0.25

ç»Ŀå¯¹

0.24

POT

0.24

æĬķåħ¥

0.24

Activations Density 0.181%

crack

No Comments

No Known Activations