INDEX

Explanations

calculations

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

æ³¾

-0.28

establish

-0.27

upplier

-0.27

é²Ķ

-0.26

ä¼łæĿ¥

-0.26

>').

-0.25

istant

-0.24

 moden

-0.24

åŃ¢

-0.24

alculate

-0.24

POSITIVE LOGITS

 favors

0.27

 sáº¯c

0.26

à¸±à¸§

0.26

 Liquid

0.26

Liquid

0.26

áº§m

0.25

erno

0.25

 ç¬

0.25

 Streets

0.25

cul

0.25

Activations Density 0.042%

calculations

No Comments

No Known Activations