INDEX

Explanations

u

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¿Ŀ

-0.32

éģ½

-0.26

è¶³è¿¹

-0.25

 commute

-0.25

æŁ

-0.25

PRESS

-0.24

ansson

-0.24

 dropout

-0.24

aceut

-0.24

 Corner

-0.24

POSITIVE LOGITS

 circulating

0.30

icus

0.25

fw

0.25

ope

0.25

.World

0.24

çº£

0.24

æ¬¾

0.24

å°ļä¹¦

0.24

ç¢¼

0.23

VEN

0.23

Activations Density 0.005%

u

No Comments

No Known Activations