INDEX

Explanations

possessive

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

èĻ¾

-0.28

haps

-0.26

 independ

-0.25

æĸ°çļĦä¸Ģå¹´

-0.25

atics

-0.24

beit

-0.24

sob

-0.24

 Mess

-0.23

degree

-0.23

 crow

-0.23

POSITIVE LOGITS

éĵ¶

0.30

cin

0.28

Silver

0.28

çľ¼åīį

0.27

çĻ½éĵ¶

0.27

 Silver

0.27

.sg

0.25

è¿ĻèĪ¬

0.24

LG

0.24

 Triple

0.24

Activations Density 0.034%

possessive

No Comments

No Known Activations