Neuron Explorer

Qwen3-0.6B

"to" after "help" plus object

A neuron in layer 1 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

The neuron fires on the word "to" in phrases like "help students to" or "helps you to", where someone is being helped to do something. Turning it up produced unrelated text, so the steering does not show this clearly.

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

    from accessing cattle water troughs, feed troughs and mineral licks, or entering farm buildings. Further information is available on the TB hub.⏎4. Help to roll out badger vaccinations⏎Badgers can be vaccinated against bTB. Bad

  2. #2 peak

    is involvement of immediate gain in academic career. It can also help you elevate your educational status and look good on a CV.⏎Honor classes can also help students to rise to the challenge of hard work, making them more poised and confident. Greater

  3. #3 peak

    can help the hospitality industry to cut costs and streamline interactions. One such example is the use of mobile electronic keys in hotels. This type of technology can help employees to check in and out of rooms more efficiently, which could mean reduced staffing costs and

  4. #4 peak

    lives or games that improve memory or numeracy skills.⏎3. Expand knowledge⏎One of the positive effects of smartphones is that they can help students to get information on different subjects very easily.⏎Smartphones are equipped with various applications,

  5. #5 peak

    part of an enzyme that is crucial for influenza virus replication.⏎The study was done on the 2009 pandemic influenza strain, but it will help scientists to design innovative drugs against all the different influenza strains, and potentially lead to a new

  6. #6 peak

    , or they may be hardware or software solutions. What matters primarily is that an ILS helps you to perform multiple tasks with the greatest ease in the least amount of time. Typical tools

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: this is the time I have been thinking about lately: this is the time I have been thinking about lately: this is the time I have been thinking about lately: this is the time I have been thinking about lately: this is the time

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

    Asia, and America. The American variety (var. Americana) is larger. Called⏎whistler, garrot, gowdy, pied widgeon, whiteside, curre, and doucker. Barrow's golden

  2. #2 peak

    , there are Polynesian figures who stole fire from the gods, and Loki, the Norse trickster god, is associated with fire. As Hans Biedermann notes in his The Wordsworth Dictionary of

  3. #3 peak

    which are open waters training, fitness and techniques. Also it is very important to protect the skin against the sun UVA and UVB radiation, and against Jellyfish and<|endoftext|>The moon is only two days past new today and is a waxing

  4. #4 peak

    -extinct frog from Sri Lanka; a highly venomous snakes from Australia; a fruit bat; a European mushroom; a jellyfish named after its victim, an American tourist who apparently died after being stung 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. L0:1301 suppresses
  2. L0:178 suppresses
  3. L0:1224 suppresses
  4. L0:83 weakly suppresses
  5. L0:1075 weakly excites
  6. L0:250 weakly suppresses
  7. L0:428 weakly suppresses
  8. L0:1993 weakly excites
  9. L0:370 weakly excites
  10. L0:1839 weakly excites
  11. L0:2092 weakly suppresses
  12. L0:191 weakly suppresses
  13. L0:36 weakly suppresses
  14. L0:3029 weakly excites
  15. L0:121 weakly excites
  16. L0:0 weakly excites
  17. L0:2712 weakly excites
  18. L0:992 weakly excites
  19. L0:89 weakly excites
  20. L0:1149 weakly excites
  21. L0:420 weakly excites
  22. L0:3010 weakly excites
  23. L0:896 weakly suppresses
  24. L0:1 weakly suppresses

Feeds later layers

  1. L14:785 weakly excites
  2. L15:874 weakly suppresses
  3. L17:1601 weakly suppresses
  4. L4:1012 weakly excites
  5. L16:1718 weakly excites
  6. L27:735 weakly excites
  7. L25:1243 weakly suppresses
  8. L12:564 weakly suppresses
  9. L23:1276 weakly suppresses
  10. L11:1993 weakly suppresses
  11. L2:2020 weakly excites
  12. L13:2211 weakly suppresses
  13. L4:823 weakly suppresses
  14. L6:998 weakly excites
  15. L8:2064 weakly suppresses
  16. L5:521 weakly suppresses
  17. L21:2504 weakly suppresses
  18. L8:917 weakly suppresses
  19. L20:906 weakly suppresses
  20. L11:3036 weakly excites
  21. L14:2635 weakly excites
  22. L2:2013 weakly suppresses
  23. L27:2932 weakly excites capital F starting a word
  24. L14:987 weakly suppresses

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.

2 values between -0.56 and -0.4128 values between -0.41 and -0.26205 values between -0.26 and -0.112822 values between -0.11 and 0.03798 values between 0.03 and 0.1845 values between 0.18 and 0.334 values between 0.33 and 0.481 values between 0.48 and 0.621 values between 0.62 and 0.771 values between 1.21 and 1.361 values between 5.19 and 5.34offnegativepositiveoften

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. �
  2. (js
  3. ما
  4. 拜
  5. 非凡
  6. �
  7. ��
  8. uset
  9. 不负
  10. 狄

Suppresses

  1. izziness
  2. ournal
  3. ária
  4. ários
  5. 理事长
  6. sheets
  7. oire
  8. écoute
  9. 却发现
  10. 院长