Neuron Explorer

Qwen3-0.6B

'always' or 'often' after 'is' or 'there is'

A neuron in layer 7 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 lights up on words like 'always' and 'often' when they sit between 'is' or 'there is' and the rest of the sentence, as in 'it is always easy'. When it was turned up, the written text did not clearly change in any way tied to this idea.

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

    challenging task but with the right anchoring script, it is always easy.⏎So here we will see how to write anchoring script or compering

  2. #2 peak

    the average rainfall is in upwards of 150″ per year. Temperature varies little, with the average temperature near 82, and the humidity is always high.⏎Figure 2. Yum! After a hard days

  3. #3 peak

    in the State and nearly 55 persons died because of complications arising out of it. However, sporadic cases continue to get reported from districts and there is always a possibility of the virus making a comeback next

  4. #4 peak

    to answer the questions that don’t require context first. (You may decide you have to read the entire passage to answer the context questions.)Staying calm is always easier said than done but remember that there is no advantage to having existing subject knowledge

  5. #5 peak

    , were almost cut off from the rest of Mallorca because of those very mountains. The tortuous, switchback road with steep climbs, hairpin bends and often cut by bad weather conditions made travel so long and arduous to Palma

  6. #6 peak

    in his time. Muhammad also appears to have been the first to suggest the contagious nature of leprosy, mange and sexually transmitted disease; and that there is always a cause and a cure for every disease, according to several hadiths in

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 have to be able to write a 1000-word essay that includes all the content, and I can use any of the content I want, as long as it is in the English language. I need to make sure that

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

    But these aren’t the kind of rechargeable batteries that you can use in place of disposables.⏎Instead, you might use nickel-cadmium batteries (NiCd). Nickel is the cathode and cadmium is the anode. The recharge

  2. #2 peak

    Acid Battery: They take longer to lose their charge when not used, making it easier to maintain your battery while away from the camper or RV.⏎Nickel Cadmium Battery: These batteries have been around a long time and can hold a lot of

  3. #3 peak

    by milling. Whole grains are better sources of fiber and other important nutrients, such as selenium, potassium and magnesium. Whole grains are either single foods, such as<|endoftext|>Of all the

  4. #4 peak

    blood pressure [*].⏎Focus on foods high in potassium too. Potassium is an electrolyte needed to balance out too much sodium, relax blood vessel walls

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. L5:599 suppresses
  2. L3:2798 excites
  3. L5:2610 excites
  4. L4:1543 suppresses
  5. L4:830 weakly excites
  6. L5:2095 weakly excites
  7. L0:3009 weakly excites
  8. L6:1622 weakly excites
  9. L4:2212 weakly suppresses
  10. L6:1283 weakly excites
  11. L5:852 weakly suppresses
  12. L6:457 weakly excites
  13. L1:1113 weakly suppresses
  14. L4:981 weakly suppresses
  15. L6:2683 weakly suppresses
  16. L6:1813 weakly excites
  17. L6:1492 weakly excites
  18. L3:1386 weakly excites
  19. L1:2236 weakly suppresses
  20. L5:1884 weakly suppresses
  21. L2:1939 weakly excites
  22. L6:17 weakly suppresses
  23. L0:37 weakly suppresses
  24. L4:1787 weakly excites

Feeds later layers

  1. L8:1056 excites
  2. L15:1829 excites
  3. L20:1607 excites
  4. L17:1603 excites
  5. L10:932 excites
  6. L17:1662 weakly excites
  7. L8:330 weakly excites
  8. L12:842 weakly excites
  9. L12:1702 weakly suppresses
  10. L8:1010 weakly suppresses
  11. L19:1111 weakly suppresses
  12. L24:2042 weakly excites
  13. L12:1320 weakly excites
  14. L9:1177 weakly excites
  15. L27:848 weakly suppresses
  16. L18:1335 weakly suppresses
  17. L17:1249 weakly excites
  18. L16:2726 weakly excites
  19. L20:2576 weakly excites
  20. L19:1011 weakly suppresses
  21. L18:2768 weakly suppresses
  22. L18:1319 weakly excites
  23. L22:1303 weakly suppresses
  24. L14:839 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 -2.08 and -1.891 values between -1.70 and -1.501 values between -0.93 and -0.749 values between -0.74 and -0.54108 values between -0.54 and -0.35750 values between -0.35 and -0.162118 values between -0.16 and 0.03797 values between 0.03 and 0.2277 values between 0.22 and 0.4216 values between 0.42 and 0.616 values between 0.61 and 0.807 values between 0.80 and 0.994 values between 1.19 and 1.382 values between 1.38 and 1.571 values between 1.57 and 1.761 values between 1.76 and 1.951 values between 1.95 and 2.152 values between 2.15 and 2.341 values between 2.34 and 2.532 values between 2.72 and 2.911 values between 4.07 and 4.261 values between 5.22 and 5.411 values between 5.41 and 5.60offnegativepositiveoften

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. TIM
  2. .Guid
  3. Editors
  4. fist
  5. addElement
  6. ystone
  7. ộc
  8. พฤ
  9. 交替
  10. 鹑

Suppresses

  1. ificate
  2. het
  3. ilogue
  4. htable
  5. 日正式
  6. 信息发布
  7. owe
  8. 权重
  9. nowled
  10. ustomed