Neuron Explorer

Qwen3-0.6B

the year '2030' ending in zero

A neuron in layer 3 of Qwen3-0.6B. Its strongest snippets are very consistent: they mostly peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on the final digit '0' in the year 2030 or similar years like 2040 or 2050, when the year is written as a target date in the future. Turning it up produced loose, unrelated text.

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 activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

  1. #1 peak

    is very familiar with the role of standards. Well-known standards, such as ISO 17799 for IT security and the ISO 9000 series for management, establish guidelines and general principles that codify industry best practices.

  2. #2 peak

    of the oceans is widely regarded as a possible solution to increase food and could be one of the next most important developments in human history. By 2050, the edible bioresource biomass will have to satisfy the 9 billion people predicted

  3. #3 peak

    production will be the most affected by climate change by 2030. This would lead to food insecurity, which in turn could lead to social instability

  4. #4 peak

    its commitment to meeting Sustainable Development Goal (SDG) 6, which is to “ensure access to water and sanitation for all” by 2030. But the National Longitudinal Phone Survey (NLPS) on the socio

  5. #5 peak

    a plan that the US has to send humans to Mars by 2030.” Space is about to get crowded, which means it’s even more important not

  6. #6 peak

    jobs and investments in frontline communities bearing the brunt of environmental injustice—they offer a blueprint for both cutting U.S. carbon emissions in half by 2030 and doing so equitably.⏎But neither plan explicitly grapples with the politically

Steering

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.

turned down a lot
Prompt

Here is something I have been thinking about lately: what is the value of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

  1. #1 peak

    versal of dysbiosis as a therapeutic model in MS⏎- Roles for short chain fatty acids, bile acids, phytoestrogens, tryptophan, choline and mucin degradation⏎And for those readers interested in data

  2. #2 peak

    almonds instead of unhealthy foods and lose weight by eating the tasty treat.⏎Another of the health benefits of almonds are good for brain development. The content of tryptoph

  3. #3 peak

    86 from a portion of Ancient Falmouth. The latter was later to be dissolved into Cape Elizabeth, Westbrook, and an additional portion of Portland, Stroudwater.⏎On March 26, 1833 Portland became a

  4. #4 peak

    sensitivity to drought. Genotypes will be subjected to drought by adding PEG 8000 to the nutritive solution (osmotic potential of -0.75 MPa). In addition to evaluating the differential production of NO by

Connections

Show on map

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Fed by earlier layers

  1. L2:148 weakly excites
  2. L2:1019 weakly suppresses
  3. L0:207 weakly suppresses
  4. L2:2646 weakly suppresses
  5. L2:1246 weakly suppresses
  6. L2:126 weakly excites
  7. L2:111 weakly suppresses
  8. L1:2507 weakly excites
  9. L2:41 weakly suppresses
  10. L0:2473 weakly excites
  11. L0:1301 weakly suppresses
  12. L0:1111 weakly excites
  13. L1:2200 weakly suppresses
  14. L2:1947 weakly excites
  15. L0:178 weakly suppresses
  16. L0:1762 weakly suppresses
  17. L2:879 weakly suppresses
  18. L1:1921 weakly suppresses
  19. L1:1734 weakly excites
  20. L2:328 weakly excites 'of' in fixed names and phrases
  21. L0:1224 weakly suppresses
  22. L1:2263 weakly suppresses
  23. L1:2010 weakly excites
  24. L1:1757 weakly suppresses

Feeds later layers

  1. L7:2273 weakly suppresses
  2. L16:2492 weakly suppresses
  3. L6:1398 weakly excites
  4. L5:542 weakly excites
  5. L22:17 weakly excites
  6. L4:468 weakly suppresses "that" after "than" or "like"
  7. L14:1527 weakly suppresses
  8. L4:2051 weakly suppresses
  9. L17:2958 weakly excites
  10. L18:729 weakly suppresses
  11. L17:606 weakly excites
  12. L16:1896 weakly suppresses
  13. L21:1378 weakly excites
  14. L14:1547 weakly suppresses
  15. L11:2180 weakly suppresses
  16. L18:1879 weakly suppresses
  17. L23:2604 weakly suppresses
  18. L10:2840 weakly suppresses
  19. L14:2226 weakly suppresses
  20. L8:2796 weakly suppresses
  21. L18:2931 weakly suppresses
  22. L6:2435 weakly excites
  23. L16:644 weakly excites
  24. L6:289 weakly excites

Activation histogram

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.

1 values between -0.96 and -0.851 values between -0.52 and -0.4121 values between -0.41 and -0.31114 values between -0.31 and -0.20508 values between -0.20 and -0.091792 values between -0.09 and 0.021155 values between 0.02 and 0.13262 values between 0.13 and 0.2440 values between 0.24 and 0.357 values between 0.35 and 0.461 values between 0.46 and 0.573 values between 0.57 and 0.681 values between 0.79 and 0.901 values between 1.33 and 1.441 values between 3.30 and 3.41offnegativepositiveoften

Logit lens

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 layers instead.

Promotes

  1. 阴影
  2. 床
  3. inished
  4. culos
  5. оцен
  6. gratuit
  7. Boom
  8. 这种方法
  9. 'é
  10. pis

Suppresses

  1. SID
  2. oram
  3. ['./
  4. onDataChange
  5. elpers
  6. су
  7. DISCLAIMED
  8. []):
  9. []);⏎
  10. 又好