names in website boilerplate
A neuronOne of thousands of tiny dials inside each layer. It reads the text so far and produces a number, its activation, that nudges what the model writes next. in layerOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. 17 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featuredA neuron picked for the full treatment: steering outputs and a written explanation. About 3,000 of the 86,000 neurons are featured., so it has steering outputs.
What this neuron does
This neuron fires on names and product words that appear in website footers, copyright lines and page blurbs, such as 'collections' in a lesson-planning site ad, 'Foundation' in a software licence, or 'Smith' in a company notice. Turned up, the model did not write about these, so its effect on the output is unclear.
Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).
Fires most on
The text windows where this neuron's activationThe number a neuron produces for a token. Large positive means it fired hard; negative means it pushed the other way. was highest. Amber marks positive activation; the outlined tokenA piece of text the model reads at once: often a word, sometimes part of a word or a punctuation mark. is the peak. Hover a token for its strength.
-
Free Trial to Unlock the Full Review⏎Why Lesson Planet?⏎Find quality lesson planning resources, fast!⏎Share & remix collections to collaborate.⏎Organize your curriculum with collections. Easy!⏎Have time to be more creative & energetic with your students!⏎Students
-
Free Trial to Unlock the Full Review⏎Why Lesson Planet?⏎Find quality lesson planning resources, fast!⏎Share & remix collections to collaborate.⏎Organize your curriculum with collections. Easy!⏎Have time to be more creative & energetic with your students!⏎Students
-
Why Lesson Planet?⏎Find quality lesson planning resources, fast!⏎Share & remix collections to collaborate.⏎Organize your curriculum with collections. Easy!⏎Have time to be
-
family from this group with four members, which is the average family size in the<|endoftext|>Why Lesson Planet?⏎Find quality lesson planning resources, fast!⏎Share & remix collections to collaborate.⏎Organize your curriculum with collections. Easy!⏎Have time to be
-
copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.3 or any later version published by the Free Software Foundation; with no Invariant Sections, no Front-Cover Texts, and no
-
. Prices and availability in WHSmith Stores may vary significantly⏎© Copyright 2013 - 2017 WHSmith and its suppliers.⏎WHSmith High Street Limited Greenbridge Road, Swindon, Wiltshire, United
SteeringAdding a push along a neuron while the model writes, to see how its output changes. Turning it up or down.
Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.
Here is something I have been thinking about lately: I have a, I have a, I have a, I have a, I have a, I have a, I have a, I have a, I have a, I have a, I have a, I have a,
Most negative on
Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.
-
of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Neither BioOne nor the owners and publishers of the content make, and they explicitly disclaim, any express or implied
-
|Math Topics:||Graphing of Data|⏎© 1994- Drexel University. All rights reserved.⏎The Math Forum is a research and educational enterprise of the Drexel University School of Education.<|endoftext|>Maybe you’ve
-
problems, and the authors also include methods that allow for the solving of nonmathematical problems as mathematical problems.⏎To view this DRM protected ebook on your desktop or laptop you will need to have Adobe Digital Editions installed. It is a free
-
nothing — not even a conservative culture or fear of the Taliban<|endoftext|>This preview shows pages 1–2. Sign up to view the full content.⏎This preview has intentionally blurred sections. Sign up to view the full version.View Full Document⏎Un
Connections
Show on mapWhich neuronsOne of thousands of tiny dials inside each layer. It reads the text so far and produces a number, its activation, that nudges what the model writes next. in earlier layersOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.
Fed by earlier layers
- L11:29 excites
- L15:1317 excites
- L16:248 excites
- L15:23 suppresses
- L10:61 suppresses
- L15:1272 suppresses
- L7:22 suppresses
- L13:129 suppresses
- L14:1641 excites
- L16:1543 suppresses
- L13:2963 suppresses
- L13:2188 excites unclear: weak, scattered tokens
- L16:2477 excites
- L10:812 excites
- L10:2957 excites
- L10:1578 excites
- L14:932 excites
- L15:2628 excites
- L15:2839 excites
- L10:46 suppresses
- L15:1795 suppresses
- L10:124 suppresses
- L14:2164 excites
- L15:1295 weakly excites
Feeds later layers
- L26:1082 suppresses
- L25:3 weakly suppresses
- L23:2606 weakly excites
- L19:772 weakly excites
- L21:2551 weakly excites
- L22:1799 weakly excites
- L25:509 weakly excites
- L18:348 weakly excites
- L25:2769 weakly excites
- L23:210 weakly excites verb right before its object
- L22:1940 weakly excites
- L21:1989 weakly excites
- L22:157 weakly excites
- L24:716 weakly excites
- L25:2354 weakly excites
- L23:124 weakly suppresses
- L22:2639 weakly suppresses
- L25:2606 weakly excites
- L25:1453 weakly excites
- L22:1822 weakly excites
- L20:543 weakly excites
- L18:2616 weakly excites
- L25:697 weakly excites
- L24:1121 weakly excites
Activation histogramA chart of how often a neuron takes each activation value.
How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.
Logit lensReading which output tokens a neuron pushes toward or away from, straight off its output weights, before the later layers have their say.
The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layersOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. instead.
Promotes
- nqu
- lup
- уш
- rophe
- عون
- omap
- Lup
- createQuery
- MATRIX
- APH
Suppresses
- side
- ışı
- gibi
- mé
- ın
- bin
- сбор
- mercial
- ž
- económica