the word 'constant' in science and maths
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. 4 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 lights up on the word 'constant' when it means a fixed value, like in physics or maths problems. Turning it up mostly made the writing drift into unrelated, repetitive text, so the steering did not show a clear link to this word.
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.
-
-shifts, 2 and which is applied as a matter of course to all measures of apparent luminosity used for the estimation of distances.⏎2 Since E = constant = h / c, the above statement assumes that the relation between Planck's
-
1)⏎When you differentiate the integral with variable upper limit it gives you the function being integrated.⏎Thus (because the lower limit doesn't play any role being a constant number)⏎dF(x)/dx2 = √(1 + t3
-
from P perpendicular to the sides of the triangle where A, B and C⏎are points on the sides. Prove that PA + PB + PC is a constant.⏎Can you decide whether two lines are perpendicular or not? Can you⏎do
-
fractional red-shift d / is constant throughout a given spectrum. Each wave-length is increased, and, consequently, the energy in each quantum is reduced, by the constant factor 1 + d / . We might naturally conclude that the total luminosity
-
(h*=h/2pi). a) Using its own inner impulse (h) circle - particle moves ( as a wheel) in a straight line with constant speed c = 1. We call such particle - ?photon?.
-
What is the centripetal force acting on a car of mass 2000 Kg turning around a circular bend of radius 50 meters at the constant speed of 36 km/hr?⏎A) 4,000
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: (click) the same as the other the same I am the same as the same I am the same as the same I am the same as the same I am the same as the same I am the same
Most negative on
Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.
-
if the electricity is imagined as water, the voltage corresponds to the water pressure, in simple terms, it is the power of electricity. Here, we will not only introduce to you where you’ll find volts in your daily life, but also list
-
fruit juices, alcohol and other highly processed drinks.⏎- Eliminate omega-6-rich vegetable oils from your diet, and use cold-pressed, extra-virgin olive oil instead.⏎- Emphasize omega-3 fats, found
-
you must understand and apply some crucial National Electrical Code rules and regulation. Following these rules to the letter will not only assure you that your work will pass inspection, but that it will be a safe
-
to rely on the price point of these cards to be the best indication of performance level. .⏎When you see a memory amount associated with a video card, this quantity has a specific benefit, even if it is different than most people believe. 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
- L2:2635 excites
- L0:178 weakly suppresses
- L0:1224 weakly suppresses
- L0:1301 weakly suppresses
- L2:111 weakly suppresses
- L2:75 weakly suppresses
- L3:187 weakly excites
- L3:855 weakly excites
- L2:2382 weakly excites
- L0:3027 weakly suppresses
- L2:1657 weakly excites
- L3:1472 weakly excites
- L3:272 weakly excites
- L3:2060 weakly excites
- L3:165 weakly suppresses
- L2:493 weakly suppresses
- L3:464 weakly excites
- L3:122 weakly excites
- L3:50 weakly excites
- L3:186 weakly suppresses
- L2:497 weakly excites
- L2:1964 weakly suppresses
- L2:3001 weakly suppresses
- L3:2107 weakly suppresses
Feeds later layers
- L8:1461 excites
- L12:1645 weakly excites
- L9:660 weakly excites
- L7:756 weakly excites
- L8:954 weakly excites vitamin D mentions
- L11:1828 weakly excites
- L12:1911 weakly excites
- L11:1430 weakly excites
- L11:2291 weakly excites numbers inside citation references
- L15:2056 weakly excites
- L15:2029 weakly excites
- L22:1841 weakly excites
- L5:1084 weakly suppresses
- L16:1676 weakly excites
- L11:1534 weakly excites
- L21:885 weakly excites
- L17:1162 weakly excites
- L11:1733 weakly suppresses
- L13:2031 weakly suppresses
- L17:2448 weakly excites
- L13:2737 weakly excites
- L27:1646 weakly excites
- L10:2666 weakly excites
- L17:1758 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
- gist
- ϊ
- .timedelta
- phon
- orable
- 可想
- alike
- Severity
- 级别
- fierc
Suppresses
- ön
- ฝ
- 答题
- BP
- submission
- cor
- aturing
- AP
- ADATA
- arra