Rh blood type and related terms
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. 9 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 is most sure about the phrase 'Rh' in blood type talk, and it also fires on a few scattered words like 'fake', 'trans fat', 'water' and 'planets'. It goes quiet or negative on word-game and spelling prompts. Turning it up did not bring back blood talk; the model drifted into temperature and repetition.
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.
-
second bottle to be the fake.⏎In practice, there are some limitations to a manual application of this geometric analysis
-
, palm and coconut oils, sugary foods and beverages, saturated fat – found mostly in foods that come from animals; trans fat (trans fatty acids) – found in foods made with hydrogenated oils and fats, such
-
we expect the brown dwarf to have properties that are different from previously known brown dwarfs and much closer to those of giant exoplanets — it could even have water clouds in its atmosphere," the paper's lead author, Michael Liu of the University
-
others with type AB blood, but can receive blood from anyone.⏎Rh (+) positive blood means that your red blood cells have D antigens on their surface. Rh (-) negative blood means that your red blood cells do not have D antigens
-
all over the world. In Caucasians, the ratio of Rh (+) to Rh (-) blood is approximately 4.5:1,
-
, but it also determines your blood type. There are two main blood groups, the ABO group and the Rh group. The ABO group is made up of A, B, AB,
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 4-digit number, and the number is 30% and 40% of the number. Also, I have a 10% and 10% of the number, and 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.
-
ible furnace. Since argon or nitrogen is used as the refining medium, there is no pollution to<|endoftext|>Aptly named, the litte Owl. Guess what? The little owl is small!⏎The Little Owl is not native to Great Britain
-
to outdoor enthusiasts, such as hikers. JanSport sold all types of bags, from day packs to backpacks.⏎Whether you’re a<|endoftext|>- Enter a word for the dictionary definition.⏎From The Collaborative International Dictionary of English v.0
-
2⏎The word "focus" uses 5 letters: C F O S U.⏎No direct anagrams for focus found in this word list.⏎List shorter words within focus, sorted by length⏎All words formed from focus by changing one letter
-
, hatching into larvae within 24 to 48 hours after fertilisation (8).<|endoftext|>Peter Wadhams’ book title is a play on words from the famous Hemingway novel, as also is the last chapter of the
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
- L6:757 excites
- L8:1948 excites
- L7:1103 suppresses 'as' in 'not as ... as' comparisons
- L8:843 weakly suppresses
- L0:1844 weakly suppresses
- L6:2227 weakly excites
- L6:2160 weakly excites
- L3:2204 weakly excites
- L8:647 weakly suppresses
- L6:2432 weakly excites
- L6:2273 weakly suppresses
- L7:1663 weakly suppresses
- L4:1921 weakly suppresses
- L6:732 weakly suppresses
- L6:1572 weakly suppresses
- L3:1765 weakly excites
- L7:1143 weakly suppresses
- L4:1741 weakly suppresses
- L7:2407 weakly excites
- L0:1556 weakly excites
- L6:1000 weakly suppresses
- L2:1623 weakly excites
- L3:2364 weakly suppresses
- L3:1904 weakly excites
Feeds later layers
- L18:1980 suppresses
- L21:1054 suppresses
- L12:2026 suppresses
- L12:2290 suppresses
- L11:2308 suppresses quantity words like 'some' and 'of'
- L12:2894 suppresses
- L17:1348 weakly suppresses
- L10:1555 weakly suppresses
- L12:2824 weakly suppresses
- L12:466 weakly suppresses
- L20:2455 weakly suppresses
- L10:2959 weakly excites
- L11:1213 weakly suppresses
- L13:1648 weakly suppresses
- L10:978 weakly suppresses
- L12:2514 weakly suppresses
- L24:1841 weakly suppresses
- L13:1846 weakly excites
- L24:1815 weakly suppresses
- L10:2835 weakly excites
- L14:1795 weakly suppresses
- L16:2718 weakly suppresses
- L10:1897 weakly suppresses
- L11:2978 weakly suppresses
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
- ropol
- iju
- .arraycopy
- yleft
- ipop
- ija
- 优势
- (push
- oha
- 从严治党
Suppresses
- crossword
- 谜
- 的事情
- Suffix
- spelling
- Regex
- 仨
- ständ
- uzzle
- spell