Neuron Explorer

Qwen3-0.6B

'of' in 'in the way of'

A neuron in layer 2 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 set phrases like 'in the way of', 'stand in the way of' and 'in the form of'. Turning it up did not produce text that clearly reflected this phrase.

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

    9.9 per cent. Dentists attribute a large part of this to poor flossing habits. Forgetfulness or a busy lifestyle often gets in the way of oral hygiene. But the truth remains that a lack of flossing regimen can

  2. #2 peak

    health service providers will need to plan for a significant increase in obesity-linked comorbidities.⏎The researchers were particularly interested to know what to expect in the way of co-morbidities, including hypertension, impaired glucose tolerance (which leads to

  3. #3 peak

    new changes back down on Earth.⏎“A lot of the things we developed to engage in the space race and space exploration eventually filtered down to the public in the way of products and services that we use today and don’t even think about,” added K

  4. #4 peak

    -In-Chief⏎Eileen Collins, the first female to command a space mission, is a determined down-to-earth woman who never let anything stand in the way of her dream.⏎August 1999: NASA, Texas: Eileen

  5. #5 peak

    interfere with your body’s chemical signals and prevent you from falling asleep quickly.⏎» Keep kids caffeine-free. While a can of soda may not stand in the way of an adult getting a good night’s sleep, the smaller body of a child can

  6. #6 peak

    that acknowledges that provider and patient may have different experiences or different goals for treatment.⏎But lack of diversity among providers and poor communication with patients can get in the way of making decisions together. To get around obstacles, the Race and Health Disparities

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: the most recent 5000.0001.0001.0001.0001.0001.0001.0001.0001

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

    ago shoreline.⏎In its 2017 plan, the city's Sustainability Advisory Board identified a need to focus on education and outreach on shoreline restoration, and to encourage private property owners to use incentives like the Storm Water Credit Program, said Elizabeth

  2. #2 peak

    who remain untreated. Single-cause models of suicide (i.e., social factors or mental illness) do not do justice to the complexity of the processes involved and, therefore, do not provide useful information about the etiology and prevention of suicide in

  3. #3 peak

    ers, infrared TMDs, and TMDs that do not have a current and valid Certificate of Calibration Testing. These devices can be challenging to read and, because they only show the

  4. #4 peak

    preserve natural habitats, educate others about their role in conservation and to protect endangered species and environments. Specifically, our program includes courses in forestry, soils

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. L0:1 weakly suppresses
  2. L0:1355 weakly excites
  3. L0:1458 weakly suppresses
  4. L1:1735 weakly excites
  5. L1:460 weakly excites
  6. L1:189 weakly suppresses
  7. L0:684 weakly suppresses
  8. L1:2661 weakly excites
  9. L1:2444 weakly suppresses
  10. L1:2689 weakly excites
  11. L0:1279 weakly excites
  12. L1:24 weakly suppresses
  13. L1:1540 weakly excites
  14. L1:186 weakly suppresses
  15. L0:1075 weakly excites
  16. L1:718 weakly suppresses
  17. L1:625 weakly suppresses
  18. L0:2127 weakly excites
  19. L0:538 weakly suppresses
  20. L0:1730 weakly suppresses
  21. L1:2119 weakly excites
  22. L0:84 weakly suppresses
  23. L0:1751 weakly suppresses
  24. L0:1833 weakly excites

Feeds later layers

  1. L3:1191 weakly suppresses
  2. L10:672 weakly suppresses
  3. L9:835 weakly suppresses
  4. L8:2175 weakly excites
  5. L15:211 weakly excites
  6. L11:432 weakly suppresses
  7. L23:2992 weakly suppresses unclear: first pieces of split words
  8. L22:1502 weakly excites
  9. L24:2148 weakly excites
  10. L13:1241 weakly excites
  11. L14:952 weakly suppresses
  12. L20:1906 weakly suppresses
  13. L14:1244 weakly suppresses
  14. L8:2023 weakly suppresses
  15. L11:1650 weakly suppresses
  16. L16:2901 weakly suppresses
  17. L23:2179 weakly suppresses
  18. L7:956 weakly suppresses
  19. L22:2208 weakly suppresses
  20. L5:2906 weakly excites
  21. L18:1698 weakly suppresses
  22. L9:522 weakly suppresses
  23. L4:160 weakly suppresses
  24. L16:422 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 -5.02 and -4.861 values between -4.86 and -4.701 values between -4.53 and -4.371 values between -4.37 and -4.201 values between -3.71 and -3.551 values between -3.39 and -3.221 values between -2.40 and -2.241 values between -1.91 and -1.751 values between -1.42 and -1.262 values between -1.26 and -1.091 values between -1.09 and -0.931 values between -0.93 and -0.775 values between -0.77 and -0.604 values between -0.60 and -0.4423 values between -0.44 and -0.27375 values between -0.27 and -0.112387 values between -0.11 and 0.05970 values between 0.05 and 0.2299 values between 0.22 and 0.3819 values between 0.38 and 0.556 values between 0.55 and 0.712 values between 0.71 and 0.871 values between 0.87 and 1.041 values between 1.04 and 1.201 values between 1.20 and 1.372 values between 1.37 and 1.53offnegativepositiveoften

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. itable
  2. 或者其他
  3. 텀
  4. .Gravity
  5. Deployment
  6. qué
  7. .getElementsByName
  8. arbitrary
  9. 纬
  10. обы

Suppresses

  1. res
  2. xba
  3. resc
  4. [res
  5. 小时前
  6. idor
  7. izr
  8. nist
  9. rê
  10. edo