Neuron Explorer

Qwen3-0.6B

"in" after "shown" (figure references)

A neuron in layer 21 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 responds to the word "in" when it follows "shown" or "as shown" and points to a figure, as in "as shown in the figure". Turning it up made the model repeat phrases like "as shown in the figure" over and over.

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

    the linear movement as far as possible. Based on the analysis of the tooth surface cutting movement, the revolution and rotation of the blade are further analyzed, as shown in the figure.<|endoftext|>Source: The Independent – independent.co.uk⏎Up, Up

  2. #2 peak

    sample. It is a very sensitive technique that requires a very high vacuum (10-9~10-11 mbar). As schematically shown in Figure 1, a pulsed beam of primary ions (usually Cs or Ga

  3. #3 peak

    several phases on the stator. The rotor is toothed and made of metal, but is not permanently magnetized. A simplified variable reluctance stepping motor is shown in Figure 2. In this figure, the rotor has four teeth and the st

  4. #4 peak

    as Poisson’s equation. Geometry is assumed to be circular and windings are modeled as current sheets placed on the core surface. The induction machine geometry is shown in Figure 2. Poisson’s equation is solved analytically for geometry and

  5. #5 peak

    .⏎One of the most common applications of lead screws is for positioning the print head in 3D printers. They often use 8mm lead screws as demonstrated in the video below. The concepts explained above are all shown in the first few seconds

  6. #6 peak

    colored glass (usually red), to make lights monochromatic. The lamp is connected to a battery source through an ammeter and a rheostat as shown in the figure.⏎The optical pyrometer works in a certain simple

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 a 300-100-100-100-100 - 100 - 100 - 100 - 100 - 100

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

    10, p. 252) considered them older fluvio-glacial drifts. Thomson (1917, p. 411) refers to them more fully, but is extremely

  2. #2 peak

    ability; (2) stability over time; (3) affect on individual behaviour, and; (4) sense of shared values between the members (Ibid.).⏎Old institutionalism focus on the formal institutions, meaning law and government,3

  3. #3 peak

    for viewers moving through the decorated house, arguing that memory played a vital role in the creation and reception of Roman pictorial ensembles in domestic situations.”Ibid., 225. As I explore the continued vitality of the household memory theater

  4. #4 peak

    firepower over and over again.” William Rosenau, Book Note, The Origins of the First Modern Weapon, TECH. REV., Jan. 1987, at 74, (reviewing John Ellis,

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. L16:1709 excites
  2. L20:3063 suppresses
  3. L20:440 suppresses
  4. L19:1490 excites
  5. L19:943 excites
  6. L18:1101 excites
  7. L17:2311 excites
  8. L20:388 suppresses
  9. L14:1411 excites
  10. L3:860 suppresses
  11. L17:2176 suppresses
  12. L17:1072 weakly suppresses
  13. L14:227 weakly excites
  14. L20:2462 weakly excites
  15. L19:2654 weakly excites
  16. L18:2656 weakly excites
  17. L20:223 weakly excites
  18. L20:1679 weakly suppresses
  19. L18:2047 weakly suppresses
  20. L8:933 weakly suppresses words introducing an example or aside
  21. L20:1413 weakly excites
  22. L8:1796 weakly suppresses
  23. L19:579 weakly suppresses
  24. L3:286 weakly excites

Feeds later layers

  1. L27:2066 strongly excites
  2. L26:2455 strongly excites
  3. L23:1387 excites
  4. L22:1385 excites
  5. L23:886 excites
  6. L24:2043 excites
  7. L27:2275 excites
  8. L26:2509 excites
  9. L22:1593 excites
  10. L22:1794 excites "shown in" before a figure reference
  11. L23:1453 excites
  12. L22:960 suppresses
  13. L27:1122 excites
  14. L24:1154 excites
  15. L22:1900 excites
  16. L27:2283 excites
  17. L23:374 weakly excites
  18. L26:1020 weakly excites
  19. L27:1913 weakly excites
  20. L27:1276 weakly excites
  21. L25:2290 weakly excites
  22. L24:2854 weakly suppresses
  23. L25:791 weakly excites
  24. L24:1704 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 -4.14 and -3.812 values between -2.51 and -2.182 values between -1.85 and -1.5340 values between -1.53 and -1.20186 values between -1.20 and -0.88572 values between -0.88 and -0.551260 values between -0.55 and -0.221519 values between -0.22 and 0.10222 values between 0.10 and 0.4336 values between 0.43 and 0.7514 values between 0.75 and 1.0814 values between 1.08 and 1.4113 values between 1.41 and 1.737 values between 1.73 and 2.063 values between 2.06 and 2.393 values between 2.39 and 2.713 values between 2.71 and 3.043 values between 3.36 and 3.691 values between 3.69 and 4.021 values between 4.34 and 4.672 values between 4.67 and 4.991 values between 5.32 and 5.651 values between 5.97 and 6.301 values between 7.60 and 7.931 values between 8.58 and 8.91offnegativepositiveoften

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. Figure
  2. Figure
  3. figure
  4. figure
  5. Fig
  6. Fig
  7. Figures
  8. fig
  9. 图
  10. FIG

Suppresses

  1. quán
  2. ộng
  3. wald
  4. EmailAddress
  5. groupName
  6. Taste
  7. zá
  8. izable
  9. democratic
  10. 漱