INDEX

Explanations

growth/development

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

obil

-0.26

åĸ»

-0.26

 urgently

-0.25

.MSG

-0.25

phas

-0.25

chestra

-0.25

eteria

-0.25

zsche

-0.25

emsp

-0.24

atoria

-0.24

POSITIVE LOGITS

 Rural

0.27

å½Ī

0.27

 Depths

0.26

ä¸ĢåĽŀäºĭ

0.26

å°±æĺ¯è¿Ļæł·

0.26

å¼¹

0.25

 Revenge

0.24

æł¹æľ¬æ²¡æľī

0.24

 chart

0.24

åĨľ

0.24

Activations Density 0.003%

growth/development

No Comments

No Known Activations