'to' after a noun that needs a purpose clause
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. 7 of Qwen3-0.6B. Its strongest snippets are very consistent: they mostly peak on the same token. 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 the word 'to' when it follows a noun or phrase and introduces what is needed or intended, as in 'how much exercise do we need to' or 'the minimum age to'. Turning it up made the writing drift toward numbers and counting problems.
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.
-
. Slovin's formula allows a researcher to sample the population with a desired degree of accuracy. It gives the researcher an idea of how large his sample size needs to be to ensure a reasonable accuracy of results. * When to Use Slovin's
-
at which ice sheets have ever been seen to move over rock and into the sea, both in Antarctica and in Greenland.⏎They then calculated how much ice would need to be released into the oceans in order for sea-levels to rise by 2
-
of 0.02). Plug your population size and required margin of error into the formula. The result will be the number of samples you need to take.⏎For example, suppose that you have a group of 1,0
-
MRI scan, so researchers will know how many children are needed to conduct a successful study. The team is also exploring ways to reassure children that an
-
Let’s assume that we have a more general problem. There are n questions, and a(n) is the smallest number of times we need to take the test to guarantee that we can figure out the answers. First we can try all combinations of
-
mentioned below:⏎- Will the illegalization of abortion increase backstreet abortions?⏎- How does abortion affect a woman’s health?⏎- What should be the minimum age to legally abort?⏎- What reasons exists behind the decision of abortion for married couples?⏎
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: For example, a rectangle is a rectangle. The second is a list of lists. For example, the second is a list of lists. The second is a list of lists. The second is a list of lists. The second is a
Most negative on
Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.
-
to draw and write to show their mathematical thinking.⏎Contents 4-8 Counting and Cardinality Task Cards (CC) 9-13 Numbers and Operations in Base Ten Task Cards (NBT) 14-18 Operations
-
ivut||678 - 687|⏎|Julkaisu||JOURNAL OF LANGUAGE TEACHING AND RESEARCH|⏎|DOI - pysyväislinkit
-
wind, a growing discontent with the French.Here Be Dragons⏎Trends of 'discontent'⏎View usage over:⏎'discontent' in Other Languages⏎Translation of discontent from the Collins English to Portuguese Dictionary<|endoftext|><the auberges in
-
-immune-system⏎- Kennedy, David O. “B Vitamins and the Brain: Mechanisms, Dose and Efficacy—A Review.” Nutrients, vol. 8, no. 2, Jan. 20
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
- L6:442 excites
- L6:1674 weakly suppresses
- L6:2946 weakly excites
- L6:929 weakly suppresses
- L2:2772 weakly suppresses
- L6:1304 weakly suppresses
- L6:2606 weakly suppresses
- L1:2874 weakly suppresses
- L4:913 weakly excites
- L1:2813 weakly excites
- L6:1895 weakly excites
- L6:1217 weakly excites
- L5:326 weakly excites
- L6:1352 weakly suppresses
- L6:83 weakly excites
- L6:2029 weakly suppresses row and column words in grids and tables
- L6:1214 weakly suppresses
- L3:1546 weakly suppresses
- L2:1956 weakly suppresses
- L4:2023 weakly excites
- L5:1814 weakly excites
- L4:780 weakly excites
- L6:7 weakly suppresses
- L6:2055 weakly excites
Feeds later layers
- L12:2094 excites
- L13:2390 excites limits, thresholds and how long it takes
- L12:1088 excites
- L10:520 excites
- L12:2492 weakly excites
- L10:953 weakly excites
- L11:1367 weakly excites
- L12:1641 weakly excites
- L24:1427 weakly excites
- L27:615 weakly suppresses
- L8:2682 weakly suppresses
- L9:826 weakly excites
- L12:2632 weakly suppresses
- L18:1979 weakly excites
- L12:3045 weakly excites
- L13:1812 weakly excites
- L23:1009 weakly excites
- L15:776 weakly excites
- L9:1096 weakly excites
- L13:2415 weakly suppresses
- L12:1620 weakly suppresses
- L14:510 weakly suppresses
- L20:1098 weakly suppresses
- L16:1524 weakly suppresses unclear: document ends and species names
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
- odal
- .go
- garn
- INUX
- 遣
- reap
- del
- tallest
- go
- Hits
Suppresses
- �回
- [class
- ceiver
- [Boolean
- )t
- 比利时
- ASF
- enders
- [P
- )m