Neuron Explorer

Qwen3-0.6B

"more", "drop" and other words about amount of change

A neuron in layer 3 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on words that describe how much something goes up, down or differs, such as "more", "dropped" and "drop in blood pressure". The pattern is loose, and turning it up did not give a clear theme in the model's writing.

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

    increases with the increase of precipitation. It also depend on the direction of dominant airflows at 850 hPa. In the mid-eastern region, more than 40% acid rains appear when the dominant wind directions are NW,

  2. #2 peak

    exercises, which can be changed more often while providing new stimuli to the muscles. A good rule of thumb is that a movement should be changed when the performance plateaus over several training sessions or the movement produce increasing pain that is not corrected by a

  3. #3 peak

    and other hormones linked to breast cancer.⏎One hormone the study examined was estrone, which is a form of estrogen. It was discovered that levels of this hormone dropped 9.6 percent in women who dieted, and 11.

  4. #4 peak

    8 from Section 3.1, we drew a histogram of the length of eruption of California's Old Faithful geyser and found that the distribution is symmetric. Draw a boxplot of these data. Use the boxplot and quartiles

  5. #5 peak

    9-0.965). Children were more vulnerable to rotavirus (p = 0.008, OR<|endoftext|>

  6. #6 peak

    cards held in a black hand sold for about 20 percent less than cards held in a white hand. What’s more, “the race effect was more pronounced in sales of minority player cards.”⏎The eBay study mimics a similar one from

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 been thinking about lately. The user is a set of knowledge. The user is a set of knowledge. The user is a set of knowledge. The user is a set of knowledge. The user is a set of knowledge. 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

    Piedmont⏎By Michael Fine⏎N.C Cooperative Extension⏎Every year, my family embarks on a challenge to extend our winter vegetable season later into the winter than the previous year. In 2013, our first growing season,

  2. #2 peak

    automatic switching circuit plugs into the inverter and the wall outlet. Then the appliance plugs into the automatic switching circuit.⏎The solar panel, battery, and inverter may be purchased off-the-shelf from a variety of locations. The last two parts

  3. #3 peak

    the thief will have to make payment for what he has taken; if he has no money, he himself will have to be exchanged for money, so that payment may be made.⏎And if a Levite does not give money to get back his

  4. #4 peak

    unspoken which means): from Outdated French, or from Latin significantia, from significare ‘point out, portend’. Hence the actual application form is fairly minimal, and a majority of the applicants’ info is present of their CVs

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. L0:1588 excites
  2. L1:317 weakly suppresses
  3. L2:1899 weakly excites
  4. L0:449 weakly suppresses
  5. L0:2568 weakly suppresses
  6. L2:417 weakly excites
  7. L1:533 weakly suppresses
  8. L1:501 weakly excites
  9. L0:728 weakly excites
  10. L0:953 weakly excites
  11. L2:1652 weakly suppresses
  12. L1:1251 weakly suppresses
  13. L0:2485 weakly suppresses
  14. L2:695 weakly excites
  15. L1:1013 weakly suppresses
  16. L2:786 weakly excites
  17. L2:2857 weakly suppresses
  18. L0:2029 weakly suppresses
  19. L2:1410 weakly suppresses
  20. L2:3042 weakly excites
  21. L1:840 weakly suppresses
  22. L1:662 weakly suppresses
  23. L1:955 weakly suppresses
  24. L2:940 weakly suppresses

Feeds later layers

  1. L5:189 excites
  2. L5:193 suppresses
  3. L7:1367 excites
  4. L6:557 suppresses
  5. L4:955 excites
  6. L6:1148 weakly excites
  7. L21:1544 weakly excites
  8. L10:720 weakly suppresses
  9. L17:1175 weakly excites
  10. L6:175 weakly excites
  11. L10:2940 weakly suppresses
  12. L7:783 weakly excites
  13. L5:2159 weakly excites
  14. L20:1313 weakly suppresses
  15. L8:276 weakly excites
  16. L8:724 weakly excites
  17. L4:244 weakly suppresses
  18. L7:1920 weakly excites
  19. L13:173 weakly suppresses
  20. L10:1941 weakly suppresses
  21. L22:2341 weakly excites
  22. L4:1635 weakly excites 'light' as an adjective (pale, not heavy)
  23. L17:1766 weakly suppresses
  24. L10:455 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 -1.28 and -1.201 values between -1.04 and -0.961 values between -0.96 and -0.871 values between -0.87 and -0.792 values between -0.79 and -0.714 values between -0.71 and -0.637 values between -0.63 and -0.5510 values between -0.55 and -0.4717 values between -0.47 and -0.3942 values between -0.39 and -0.31113 values between -0.31 and -0.22286 values between -0.22 and -0.14581 values between -0.14 and -0.061365 values between -0.06 and 0.02823 values between 0.02 and 0.10353 values between 0.10 and 0.18143 values between 0.18 and 0.2669 values between 0.26 and 0.3516 values between 0.35 and 0.4321 values between 0.43 and 0.5113 values between 0.51 and 0.595 values between 0.59 and 0.678 values between 0.67 and 0.753 values between 0.75 and 0.837 values between 0.83 and 0.915 values between 0.91 and 1.001 values between 1.00 and 1.081 values between 1.08 and 1.161 values between 1.16 and 1.242 values between 1.24 and 1.321 values between 1.32 and 1.401 values between 1.40 and 1.481 values between 1.65 and 1.731 values between 1.89 and 1.97offnegativepositiveoften

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. rido
  2. 绮
  3. plotted
  4. национа
  5. 回暖
  6. orgas
  7. plot
  8. 停滞
  9. 丰满
  10. Consort

Suppresses

  1. KG
  2. KB
  3. 款
  4. $
  5. 筐
  6. 료
  7. eyes
  8. tamb
  9. n