Neuron Explorer

Qwen3-0.6B

commas before a continuation clause

A neuron in layer 13 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 small word or comma that sits just before a clause finishes or a new part of a sentence begins, such as 'and', 'but' or 'which', in long sentences. Turning it up or down gave loose, wandering text with no clear theme.

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

  1. #1 peak

    biologist at the University of Arizona in Tucson.⏎"They had no idea what it ate. But perhaps they knew that jumping spiders were cat-like in their movements, and [they] decided to name the spider after the agile panther Bagheera in

  2. #2 peak

    who We carried (in the Ark) with Noah, and of the posterity of Abraham and Israel of those whom We guided and chose. Whenever the Signs of (Allah) Most Gracious were rehearsed to them, they would fall down

  3. #3 peak

    over future developments in NT may halt this new field are also valid. Some community nervousness is certainly justified since “these technologies offer the potential for great benefit, [but] it is not benefit unalloyed.”12⏎However,

  4. #4 peak

    to great violence, with swelling, soreness to the touch, and sometimes redness of the skin…. This is a very formidable and extremely painful disease, [and] generally continues for many weeks…. The consequences of this disorder are often painfully

  5. #5 peak

    amyotrophic lateral sclerosis (ALS) and Huntington’s disease, but don’t always activate the right proteins at the right time, a recent study shows.⏎“[The cells] do not always realize there is a problem, or know how to

  6. #6 peak

    [and] having a forest products industry that begins to move toward oaks. If these come true, that's going to change the nature of the industry and [it] will [have to] adapt. [Awareness of climate change]

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: I need to be honest about the fact that the information is too accurate for the future of the world. The information is accurate for the future of the world. The information is accurate for the future of the world. Information accurate for the world

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

    z, 2011.⏎"Purchasing Power Parity Exchange Rates for the Global Poor,"⏎American Economic Journal: Applied Economics,⏎American Economic Association, vol. 3(2), pages 137-66, April

  2. #2 peak

    manner suggesting that they play a role in setting up or maintaining the 180 degrees rotational symmetry of the two flagella.⏎Rights and Permissions⏎Citation: J Cell Biol. 1983 Sep;97(3):

  3. #3 peak

    discussion of Mencius' views, the development of his ideas in the Sung and Ming and by contemporary Neo-Confucians is also considered|⏎|Keywords||No keywords specified (fix it)|⏎|Through your library||Configure|⏎Similar

  4. #4 peak

    important points of With Clause in oracle. In following section i would like to explain about the syntax as well as multiple examples of with clause.⏎With SQL_Query_Name As⏎Select * from New_SQL_Query_name;⏎Execution of With Clause :⏎In this

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. L12:2933 suppresses
  2. L9:2279 weakly excites
  3. L9:1443 weakly suppresses
  4. L11:2191 weakly excites unclear: brackets and parentheses in text
  5. L8:4 weakly excites
  6. L9:2328 weakly excites
  7. L4:1947 weakly suppresses
  8. L7:174 weakly suppresses
  9. L7:933 weakly excites
  10. L8:7 weakly excites
  11. L12:1172 weakly suppresses
  12. L8:10 weakly excites
  13. L6:2894 weakly excites
  14. L8:1332 weakly suppresses
  15. L6:801 weakly excites
  16. L6:2454 weakly suppresses
  17. L7:2485 weakly excites
  18. L6:2783 weakly excites
  19. L9:2143 weakly excites
  20. L3:2734 weakly suppresses
  21. L7:1575 weakly suppresses
  22. L3:610 weakly excites
  23. L12:804 weakly excites
  24. L12:1826 weakly suppresses

Feeds later layers

  1. L14:2191 excites
  2. L14:774 suppresses
  3. L16:1447 excites
  4. L18:2120 excites
  5. L18:1247 weakly suppresses
  6. L22:986 weakly suppresses
  7. L22:637 weakly excites
  8. L19:2371 weakly suppresses
  9. L19:1678 weakly excites
  10. L16:2805 weakly suppresses
  11. L16:52 weakly excites
  12. L20:1096 weakly suppresses
  13. L16:2350 weakly suppresses
  14. L26:1824 weakly suppresses
  15. L20:1733 weakly suppresses
  16. L14:2664 weakly excites
  17. L14:1810 weakly excites
  18. L15:3030 weakly suppresses
  19. L20:1281 weakly suppresses
  20. L22:2921 weakly suppresses
  21. L23:2242 weakly suppresses
  22. L19:542 weakly suppresses
  23. L26:356 weakly suppresses
  24. L16:892 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.

3 values between -0.78 and -0.712 values between -0.71 and -0.645 values between -0.64 and -0.5810 values between -0.58 and -0.5131 values between -0.51 and -0.4476 values between -0.44 and -0.37140 values between -0.37 and -0.30267 values between -0.30 and -0.23419 values between -0.23 and -0.16624 values between -0.16 and -0.09715 values between -0.09 and -0.02717 values between -0.02 and 0.05428 values between 0.05 and 0.12248 values between 0.12 and 0.19116 values between 0.19 and 0.2657 values between 0.26 and 0.3331 values between 0.33 and 0.4012 values between 0.40 and 0.473 values between 0.47 and 0.542 values between 0.54 and 0.611 values between 1.16 and 1.231 values between 1.93 and 2.00offnegativepositiveoften

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. ot
  2. 书
  3. �
  4. inge
  5. LAB
  6. potentially
  7. .language
  8. jąc
  9. Zend
  10. .bind

Suppresses

  1. eel
  2. ategorical
  3. igsaw
  4. (super
  5. 舄
  6. 世界第一
  7. trys
  8. rious
  9. hec
  10. ivering