Neuron Explorer

Qwen3-0.6B

'of' after 'Because'

A neuron in layer 3 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 word "of" in the phrase "Because of" at the start of a sentence. Turned up, the model's text wandered into random topics, with no clear link to the trigger.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    and continue to lower the climate impacts of cotton production.⏎Because of fertilizer’s outsized impact on GHG emissions, Cotton Incorporated has launched a coordinated

  2. #2 peak

    scholarship above suspicion and his accusers guilty of slander. The damage done his reputation, however, survived him because of historians who failed to report his rehabilitation.⏎Because of his personal qualities as well as his scientific adventures Hell was held in high esteem by

  3. #3 peak

    the same size. Creating a RAID 5 volume with components of different sizes results in unused disk space.⏎Because of the complexity of parity calculations, volumes with greater than about 20 percent writes

  4. #4 peak

    "awn," attached to each seed. Beardless varieties are generally preferred for forage, but the bearded varieties have proven resistant to deer in Pennsylvania.⏎Because of the different purposes of the grain, there are many varieties

  5. #5 peak

    automation. Thanks to its controllable IO (input-output) pins, sensors and other hardware can be read out and controlled very easily. Because of this and its low price, it is also a very popular way to get started

  6. #6 peak

    results. Governments use it for elections, services and disaster alerts. The global financial system—bank transfers, stock trades—increasingly relies on it.⏎Because of abstraction and the distributed nature of cloud computing, no single data centre holds all the

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 the importance of my name. I have been thinking about the importance of my name. I have been thinking about the importance of my name. I have been thinking about the importance of my name... and so on,

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

    summer, create shade with a retractable awning, an umbrella or trees. "Look at the gifts and challenges that nature gives

  2. #2 peak

    016/index.html<|endoftext|>Glacier Park's cold winters, short growing seasons and high altitudes are less than ideal for reptiles. These animals are ectothermic, meaning they gather body heat from their surroundings. There are only three species

  3. #3 peak

    world of fun trivia quizzes and quiz games:⏎The Battle of Badr⏎"The Battle of Badr was a key battle in Islam's struggle for independence. Outnumbered greatly, the victory at Badr gave the army great hope and is mentioned

  4. #4 peak

    Frye, 1956, p. 106 – 119]. However, according to the norms of the Sogdian language, this name could not be transformed from a word vihara for

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. L2:1880 weakly excites
  2. L1:2342 weakly excites
  3. L2:122 weakly excites
  4. L2:977 weakly excites
  5. L1:2801 weakly excites
  6. L2:2979 weakly suppresses
  7. L1:2154 weakly suppresses
  8. L0:2645 weakly excites
  9. L2:549 weakly suppresses
  10. L2:171 weakly suppresses
  11. L1:2643 weakly excites
  12. L1:858 weakly excites
  13. L1:2249 weakly suppresses
  14. L1:1588 weakly suppresses
  15. L2:1873 weakly excites
  16. L0:1256 weakly excites
  17. L1:1997 weakly excites
  18. L0:1873 weakly excites
  19. L0:1301 weakly suppresses
  20. L2:1657 weakly excites
  21. L1:2776 weakly suppresses
  22. L0:2830 weakly excites
  23. L0:1224 weakly suppresses
  24. L2:2565 weakly suppresses

Feeds later layers

  1. L4:1535 excites
  2. L9:2052 excites 'because' and 'that' after a reason
  3. L6:2143 excites
  4. L18:2841 weakly excites
  5. L5:914 weakly excites
  6. L25:2438 weakly suppresses
  7. L4:1787 weakly excites
  8. L9:2552 weakly suppresses
  9. L15:1163 weakly excites
  10. L23:635 weakly suppresses
  11. L15:1987 weakly excites
  12. L4:2117 weakly suppresses
  13. L9:1465 weakly excites
  14. L13:3017 weakly excites
  15. L5:763 weakly excites
  16. L8:1864 weakly excites
  17. L16:2206 weakly suppresses
  18. L10:1344 weakly excites
  19. L27:1918 weakly suppresses
  20. L17:3039 weakly excites
  21. L4:1500 weakly excites
  22. L16:2043 weakly excites
  23. L4:712 weakly suppresses
  24. L25:1004 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 -2.13 and -1.912 values between -1.05 and -0.845 values between -0.84 and -0.626 values between -0.62 and -0.41164 values between -0.41 and -0.192132 values between -0.19 and 0.021477 values between 0.02 and 0.2494 values between 0.24 and 0.458 values between 0.45 and 0.676 values between 0.67 and 0.883 values between 0.88 and 1.101 values between 1.10 and 1.311 values between 1.31 and 1.531 values between 1.53 and 1.741 values between 1.96 and 2.171 values between 2.17 and 2.391 values between 4.54 and 4.751 values between 4.75 and 4.971 values between 5.18 and 5.401 values between 5.83 and 6.041 values between 6.26 and 6.47offnegativepositiveoften

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. eload
  2. :=⏎
  3. latest
  4. gens
  5. //=
  6. изации
  7. 导致
  8. overcoming
  9. 甍
  10. !!,

Suppresses

  1. ibrate
  2. itemprop
  3. etermine
  4. ypy
  5. swore
  6. ady
  7. .describe
  8. dispos
  9. liber
  10. 告诉我