INDEX

Explanations

:

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

-0.28

æ¯Ķ

-0.27

format

-0.27

 PhÃº

-0.26

 Eyes

-0.26

-0.25

eyes

-0.25

æģ

-0.24

ys

-0.24

ph

-0.24

POSITIVE LOGITS

åľ°ä¸Ĭ

0.28

kÃ¶rper

0.25

 motions

0.25

ARGV

0.24

 prompts

0.24

auer

0.24

ERY

0.24

èĢ³è¾¹

0.24

arget

0.23

Ã©ri

0.23

Activations Density 0.049%

:

No Comments

No Known Activations