unclear: mid-word fragments, often 'char'
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. 24 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
It fires on a fragment in the middle of a split word, such as the piece of 'ugali' or 'unsigned', and it is strongest in the middle of a word rather than at the start. Turning it up made the model repeat 'char' and similar code-type words, while turning it down pushed the text toward unrelated phrases.
Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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.
-
food such as ugali. Common traditional vegetables include⏎baobab, cowpeas, am
-
(RBM), deep belief networks (DBN) and deep convolutional neural networks (CNN). In recent years, CNN-based methods have gained popularity<|endoftext|>typedef unsigned int size_t;⏎This type is used to hold size definitions. Since sizes are
-
have occurred in areas with an abundance of young rabbits. My sightings have been in the morning hours or at dusk. When my wife and I were in the High Uintahs, we witnessed a Canadian Lynx. It was in an area where
-
ate character in block of memory⏎Searches within the first num bytes of the block of memory pointed by ptr for the first occurrence of value (interpreted as an unsigned char), and returns a pointer to it.⏎Both value and each of the bytes
-
the labor force and future careers. Please be sure to visit www.LL-inc.org for activities to facilitate career-conversation with your young leader.<|endoftext|>How does Utterson perceive the relationship between Jekyll and Hyde for most of the novel? Is
-
’re concerned about a child’s vaping habits. In case you have any concerns about exactly where and the way to utilize น้ำยาบุหรี่ไฟฟ้าราคาส่ง ยก ลัง, you can e
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: we can take 20000000000000000000000000000000000000000000
Most negative on
Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.
-
, which looms on the horizon north of the major city of Yogyakarta, is on the island of Java.⏎President Susilo Bambang Yudhoyono has called the volcanic eruptions a crisis situation. He and several
-
of Indonesia's most active volcanoes and lies in one of the world's most densely populated areas. Many people raise crops and livestock in its shadow.⏎Yudhoyono has announced that residents will receive compensation for livelihoods and animals lost to
-
our democracy for better results throughout the history.⏎Influence by different rulers, the city has been home to different design masterpiece such as Indraparastha, Daulatabad, Old Delhi and many more. Sur
-
prevents damage from overloading. Then there is a bridge rectifier made of four 1N4007 PN junction diodes and a filter capacitor of 2.2uF/450V.⏎This<|endoftext|>Warning: Use
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
- L23:1647 excites
- L22:563 suppresses
- L21:2222 suppresses
- L20:936 suppresses
- L21:448 weakly excites
- L17:343 weakly suppresses
- L4:368 weakly excites
- L9:214 weakly excites
- L6:1313 weakly excites
- L20:431 weakly suppresses
- L4:2089 weakly suppresses
- L20:2148 weakly excites
- L20:669 weakly suppresses
- L5:173 weakly excites
- L11:1402 weakly excites
- L1:2015 weakly suppresses
- L1:419 weakly suppresses
- L19:542 weakly suppresses
- L18:3020 weakly excites
- L19:2093 weakly excites
- L11:840 weakly suppresses
- L22:1136 weakly excites
- L23:728 weakly excites
- L9:2068 weakly excites
Feeds later layers
- L27:1623 weakly excites
- L25:2905 weakly suppresses
- L26:541 weakly excites
- L27:1049 weakly excites
- L25:260 weakly suppresses
- L25:2142 weakly excites
- L26:1463 weakly suppresses
- L25:1606 weakly excites
- L27:1073 weakly excites
- L25:1380 weakly suppresses
- L27:2872 weakly excites
- L25:398 weakly excites
- L25:1994 weakly excites
- L25:2029 weakly excites
- L25:1261 weakly excites
- L25:511 weakly excites
- L25:1349 weakly excites
- L25:2847 weakly excites
- L27:2659 weakly excites
- L26:1867 weakly suppresses
- L25:2491 weakly excites
- L26:2445 weakly suppresses
- L25:2522 weakly suppresses
- L25:1118 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
- char
- char
- →char
- (char
- Char
- Char
- byte
- [char
- -char
- Character
Suppresses
- перв
- verity
- uspended
- oins
- 社区
- nous
- YGON
- 恋
- ła
- Community