Neuron Explorer

Qwen3-0.6B

"the" in "to the next"

A neuron in layer 27 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 "the" in phrases like "from one level to the next" or "until the next". Turning it down makes the model repeat the word "next" 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

    example⏎84 rounded to the nearest ten would be 80.⏎Numbers that end in a digit of 5⏎or more should be rounded up to the next

  2. #2 peak

    children between the ages of two and five. Color is also used to emphasize the different layers lodged inside the toy.⏎In order to successfully progress from one level to the next, the child needs to find the correct orientation for each piece that will enable

  3. #3 peak

    100 to get the percent. This method is also useful for finding the exact value of the number. Once you have the answer, you can move onto the next step in interpreting the result.⏎The first step in finding the percentage of a

  4. #4 peak

    point. For example, if the gradient magnitude is 2.5 and the learning rate is 0.01, then the gradient descent algorithm will pick the next point 0.025 away from the previous point.⏎If you

  5. #5 peak

    explore side-branches, they make mistakes. The “right answer” – the proof, the demonstration – simply sets a mile-marker between one phase of discovery and the next.⏎In our Math Circles, young people invent and discover their shared way

  6. #6 peak

    . Once your child runs out of cash in an envelope, they have met their budget for that pay period and are unable to spend any more in that category until the next pay period. Creating a challenge encourages your kids to ask themselves important questions:

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: next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next next

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

    tiny wasps in the Encarsia genus. Integrated pest management specialists with the University of California, Davis recommend avoiding the use of pesticides containing diazinon, carbaryl, pyrethroids and imidacloprid when caring for

  2. #2 peak

    country, there has been a rapid decline of both native plant and animal species. Some introduced plants have become invasive, taking over where wild plants once thrived. Planting native plants in your backyard is a step towards preserving your own

  3. #3 peak

    ⏎- Maximize use of lubricants in service⏎- Reduce maintenance and lubrication costs⏎- Extend equipment component life⏎Tests for oil condition include:⏎- Viscosity measures the resistance of a fluid to flow, is the most important property

  4. #4 peak

    plant⏎Brambles (rubus spp.) — blackberries/dewberries⏎Grape (vitis spp.) — muscadine⏎Greenbriar (smilax

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. L23:1339 strongly suppresses
  2. L24:1027 strongly suppresses
  3. L26:1578 strongly excites
  4. L23:2609 strongly excites
  5. L20:2152 strongly suppresses
  6. L22:2156 strongly suppresses
  7. L19:2997 strongly suppresses
  8. L23:2678 suppresses
  9. L21:2426 suppresses
  10. L20:1858 suppresses
  11. L19:1736 suppresses
  12. L18:3047 suppresses
  13. L8:14 excites
  14. L18:2132 suppresses
  15. L22:2671 excites
  16. L22:1183 suppresses
  17. L26:1564 excites
  18. L22:201 excites
  19. L8:7 excites
  20. L22:2338 suppresses
  21. L16:2387 suppresses
  22. L25:2579 excites
  23. L22:1953 excites
  24. L5:110 suppresses

Feeds later layers

None: this is the last layer.

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 -16.48 and -15.561 values between -12.78 and -11.861 values between -11.86 and -10.932 values between -10.93 and -10.011 values between -7.23 and -6.311 values between -5.38 and -4.462 values between -4.46 and -3.531 values between -3.53 and -2.6110 values between -2.61 and -1.6844 values between -1.68 and -0.76928 values between -0.76 and 0.172723 values between 0.17 and 1.09175 values between 1.09 and 2.0212 values between 2.02 and 2.943 values between 2.94 and 3.871 values between 6.64 and 7.571 values between 12.19 and 13.121 values between 19.59 and 20.52offnegativepositiveoften

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. eken
  2. altimore
  3. itudes
  4. obody
  5. uros
  6. DET
  7. инфек
  8. 檔
  9. juana
  10. êu

Suppresses

  1. next
  2. next
  3. Next
  4. Next
  5. (next
  6. →next
  7. _next
  8. .next
  9. [next
  10. ,next