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

 base

-0.31

tha

-0.29

amous

-0.28

Bet

-0.27

Base

-0.26

inc

-0.26

base

-0.26

äººå¤§ä»£è¡¨

-0.25

loth

-0.25

 Base

-0.25

POSITIVE LOGITS

legg

0.29

äº¤æį¢

0.28

æĦıå¤§

0.27

èĩªèĲ¥

0.26

.node

0.26

éĺ¶

0.26

 pragma

0.26

ilee

0.24

“Oh

0.24

[node

0.24

Activations Density 1.631%

;

No Comments

No Known Activations