Neuron Explorer

Qwen3-0.6B

digit 1 in COVID-19 and 1941

A neuron in layer 10 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 reacts to the digit 1 in COVID-19 and in years like 1941. Its opposite side lights up on words like climate and warming in discussions of climate change. Turning it up did not produce a visible theme in the output.

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

    the efficacy of its anti-malarial properties.⏎Currently, several trials which are being conducted around the world seem to indicate evidence to use this drug for COVID-19. I caution that these are preliminary results. In previous scientific publications it appears

  2. #2 peak

    a long time. And also, we are able to detect early disease,” Gouma said.⏎Researchers utilizing the breath test were able to identify COVID-19 in patients by observing how the virus reacts with oxygen, nitric oxide,

  3. #3 peak

    health of women throughout their lives. … A professional in midwifery is known as a midwife<|endoftext|>Clearly we are far from eradicating COVID 19 from our environment, but we do have the power to boost our own defenses

  4. #4 peak

    due to an underground coal-mine fire that’s been burning since 1962, which has made it too hazardous to live there; and Oradour-sur-Glane, France, a town that lost 600 lives and

  5. #5 peak

    dragged into war. In 1940 Japan with threats of force entered French Indochina. Finally, on December 7, 1941, Japan launched an armed attack on the United States, followed immediately by declarations of

  6. #6 peak

    of the cellular life forms that they infect; they turn the metabolism—the energy—of any cell that they infect into the reproduction of that virus. For COVID-19 we are fuel for the fire.⏎When

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: [Context] I'm writing a story about a character who is trying to do something specific things. I'm writing a story where a character is in a state of [X], and [X] is also a character with a specific name

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

    are increasingly being used for a range of biodiversity applications such as modelling the distribution of communities, ecological refuges, potential impacts under climate change, and biotic interactions (Araújo & Luoto,

  2. #2 peak

    it could become a test program for other coastal communities around the state.⏎Hawaii has rarely been directly hit by hurricanes. However, Lee writes in the bill that warming oceans increase the risk of hurricanes for the state. The bill estimates that if a

  3. #3 peak

    shift in the bacteria's range, he said. In addition, diseases such as cholera often spread following events like flooding, which may become more common with climate change, Morris said.⏎Other waterborne diseases can come from harmful algal blooms,

  4. #4 peak

    have been broken. The conditions have been so extreme that wildfires have broken out in Sweden and the UK.⏎Heatwaves are one of the most likely consequences of climate change. As the average global temperature rises due to higher levels of greenhouse gases, more

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. L9:956 excites
  2. L9:271 suppresses
  3. L9:1906 excites
  4. L8:1545 excites
  5. L8:2230 suppresses
  6. L8:1469 suppresses
  7. L6:932 weakly excites
  8. L8:2342 weakly suppresses
  9. L8:1760 weakly excites
  10. L9:2155 weakly excites
  11. L8:2346 weakly suppresses
  12. L9:902 weakly excites covid and pandemic news words
  13. L2:2759 weakly suppresses
  14. L6:2050 weakly suppresses
  15. L5:951 weakly excites
  16. L5:2760 weakly excites
  17. L8:929 weakly excites
  18. L9:1299 weakly suppresses
  19. L6:1162 weakly excites
  20. L2:1732 weakly excites
  21. L1:1119 weakly suppresses
  22. L3:1212 weakly suppresses
  23. L2:2070 weakly suppresses
  24. L7:2619 weakly suppresses

Feeds later layers

  1. L13:2397 excites
  2. L11:1528 excites
  3. L16:602 suppresses
  4. L18:1961 suppresses
  5. L13:328 weakly suppresses
  6. L11:1287 weakly suppresses
  7. L19:1458 weakly suppresses
  8. L20:3060 weakly suppresses
  9. L14:1412 weakly suppresses
  10. L11:1103 weakly suppresses
  11. L16:1964 weakly excites
  12. L16:1551 weakly excites
  13. L11:1316 weakly excites
  14. L16:2254 weakly suppresses
  15. L14:147 weakly suppresses
  16. L11:1409 weakly suppresses
  17. L12:1227 weakly excites
  18. L17:1850 weakly excites
  19. L17:705 weakly suppresses
  20. L12:1226 weakly suppresses
  21. L11:1731 weakly excites
  22. L11:2032 weakly excites
  23. L11:1371 weakly suppresses
  24. L11:316 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.

1 values between -5.55 and -5.341 values between -3.91 and -3.701 values between -3.29 and -3.091 values between -2.88 and -2.681 values between -2.47 and -2.275 values between -2.27 and -2.062 values between -2.06 and -1.864 values between -1.86 and -1.654 values between -1.65 and -1.455 values between -1.45 and -1.244 values between -1.24 and -1.049 values between -1.04 and -0.8424 values between -0.84 and -0.6351 values between -0.63 and -0.43229 values between -0.43 and -0.221366 values between -0.22 and -0.021595 values between -0.02 and 0.19347 values between 0.19 and 0.40121 values between 0.40 and 0.6064 values between 0.60 and 0.8034 values between 0.80 and 1.0114 values between 1.01 and 1.2110 values between 1.21 and 1.427 values between 1.42 and 1.624 values between 1.62 and 1.831 values between 1.83 and 2.031 values between 2.03 and 2.241 values between 2.24 and 2.441 values between 2.44 and 2.65offnegativepositiveoften

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. 就说
  2. 堂
  3. amsung
  4. 琬
  5. arges
  6. zano
  7. argued
  8. atitude
  9. /Gate
  10. []=$

Suppresses

  1. 墟
  2. light
  3. -fix
  4. ib
  5. hash
  6. ios
  7. 净
  8. medium
  9. emat
  10. setting