Neuron Explorer

Qwen3-0.6B

unit conversions in parentheses

A neuron in layer 13 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on the unit inside a bracketed conversion, such as the 'mi' in '0.42 sq mi' or the 'F' in a Fahrenheit reading. Turning it up did not make the text about measurements, so the link is only partly visible.

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

    and policymakers across the country who are pushing for effective and equitable climate policies in their states. The views, thoughts, and opinions expressed in this article do not necessarily reflect those of Climate XChange.⏎Interested in submitting an article to be posted on our

  2. #2 peak

    from the top of the Carlton Centre⏎|Municipality||City of Johannesburg|⏎|• Total||1.09 km2 (0.42 sq mi)|⏎|• Density||13,000/km2 (

  3. #3 peak

    to some of the more fascinating questions that really excite mathematicians. Mathematics is the study of abstraction. Mathematicians search for similar patterns in seemingly different settings and then strive to communicate those patterns precisely. Mathematics is a creative process, not a mechanical

  4. #4 peak

    , 1991|⏎|-||Total||64,589 km2 (124th)⏎24,938 sq mi⏎|-

  5. #5 peak

    ’s power.⏎While exposure to any inappropriate conditions can affect the potency of refrigerated vaccines, a single exposure to freezing temperatures (0° C [32° F] or colder) will destroy some. For example, liquid vaccines that contain

  6. #6 peak

    they are violating the negative rights of the citizens; that is, rights to have something not done to you. For example, taking money in the form of taxes to pay for such programs as described above deprives individuals of property. Proponents of

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: what is the (x) for the formulae in the formulae. So, this is the case for the formulae. I need to solve for a formula in this case. So, for example, a formula. So, the

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

    0, 2016⏎- Rogue Bras to Bogarts: April Fool’s Day in the Media - April 1, 2016⏎- Romantic Writing: The History of Valentine’s Cards - February 10,

  2. #2 peak

    of a risky asset is a random walk with drift, so its return is unpredictable."⏎4. Is the following statement true, false or uncertain? "Under full liquidity constraints the marginal propensity to consume out of current income

  3. #3 peak

    1 (2):73 – 84.⏎James Behuniak (2002). Mencius on Becoming Human. Dissertation, University of Hawaii at Manoa⏎Liang Tao & Andrew Lambert (2009

  4. #4 peak

    ocean's surface to nearly a mile down, WHOI built acoustic tracking systems that monitor the movements of whales. A key component is a transmitter secured on the backs of the research subjects. Relaying information to detection buoys, the device houses

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. L11:1116 excites
  2. L12:1263 excites
  3. L9:3062 excites
  4. L10:882 excites
  5. L12:1546 suppresses
  6. L12:1544 suppresses
  7. L12:3032 excites
  8. L12:1327 suppresses
  9. L9:2181 excites
  10. L12:867 excites
  11. L6:373 suppresses
  12. L12:1369 suppresses
  13. L12:1170 suppresses
  14. L11:1536 suppresses
  15. L12:3069 excites
  16. L10:108 weakly excites
  17. L9:797 weakly suppresses
  18. L11:1205 weakly suppresses
  19. L11:1226 weakly suppresses
  20. L11:1322 weakly excites
  21. L11:2683 weakly suppresses
  22. L8:2329 weakly suppresses
  23. L12:1805 weakly suppresses
  24. L12:9 weakly suppresses

Feeds later layers

  1. L14:1503 strongly excites
  2. L17:1229 excites
  3. L16:2759 excites
  4. L15:598 suppresses
  5. L15:1540 excites
  6. L14:981 excites
  7. L14:2022 excites
  8. L14:2313 excites
  9. L17:326 suppresses
  10. L18:2572 excites
  11. L14:1664 excites
  12. L18:1879 excites
  13. L14:2290 excites
  14. L16:2917 excites
  15. L16:2677 excites
  16. L18:250 suppresses
  17. L16:1394 suppresses
  18. L14:1609 excites
  19. L17:2365 excites
  20. L15:2450 excites
  21. L16:2512 excites
  22. L14:378 excites
  23. L15:1482 excites
  24. L17:1204 excites

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 -2.65 and -2.531 values between -2.29 and -2.171 values between -2.17 and -2.041 values between -2.04 and -1.923 values between -1.92 and -1.805 values between -1.80 and -1.682 values between -1.68 and -1.566 values between -1.56 and -1.448 values between -1.44 and -1.3211 values between -1.32 and -1.207 values between -1.20 and -1.0822 values between -1.08 and -0.9639 values between -0.96 and -0.8456 values between -0.84 and -0.7292 values between -0.72 and -0.60133 values between -0.60 and -0.47221 values between -0.47 and -0.35352 values between -0.35 and -0.23535 values between -0.23 and -0.11969 values between -0.11 and 0.01680 values between 0.01 and 0.13308 values between 0.13 and 0.25150 values between 0.25 and 0.37100 values between 0.37 and 0.4969 values between 0.49 and 0.6141 values between 0.61 and 0.7329 values between 0.73 and 0.8617 values between 0.86 and 0.9821 values between 0.98 and 1.1010 values between 1.10 and 1.225 values between 1.22 and 1.343 values between 1.34 and 1.464 values between 1.46 and 1.583 values between 1.58 and 1.702 values between 1.70 and 1.821 values between 2.06 and 2.18offnegativepositiveoften

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. :⏎
  2. :⏎
  3. :⏎⏎
  4. :⏎⏎
  5. ]:⏎
  6. :{⏎
  7. :⏎
  8. 에는
  9. //:
  10. pois

Suppresses

  1. authority
  2. <Entry
  3. .datab
  4. nth
  5. odore
  6. 感激
  7. feb
  8. Authority
  9. Supplier
  10. ninth