INDEX

Explanations

occupational environments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

def

-0.26

ä¸»åĬ¨

-0.26

å¤įæĿĤçļĦ

-0.26

 incor

-0.26

def

-0.25

ç¼©

-0.25

 experiment

-0.25

èĩªåĬ¨åĮĸ

-0.25

èıĮ

-0.24

ç½²

-0.24

POSITIVE LOGITS

*ft

0.30

htable

0.27

htt

0.27

éĻ¢éĻ¢éķ¿

0.26

è¨±

0.26

èĢģåħ¬

0.26

pond

0.25

 Ø³ÙĪØ±

0.24

éĥ½ä¸įæĺ¯

0.24

æį£

0.24

Activations Density 0.005%

occupational environments

No Comments

No Known Activations