Neuron Explorer

Qwen3-0.6B

"prices" after economic words

A neuron in layer 10 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 lights up on the word "prices," especially in economic news like "world prices," "wheat prices" or "commodity prices." Turning it up made the model write about prices, food, oil and supply, so the idea comes through clearly. The opposite side is weak and hard to read.

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

    prices for these resources. Despite Peru's strong macroeconomic performance, dependence on minerals and metals exports and imported foodstuffs makes the economy vulnerable to fluctuations in world prices.⏎Peru's rapid expansion coupled with cash transfers and other programs have helped to

  2. #2 peak

    5.6% per year from 2009-13 with a stable exchange rate and low inflation. This growth was due partly to high international prices for Peru's metals and minerals exports, which account for 55% of

  3. #3 peak

    Pakistan comes as a drought and wildfires in Russia have cut the harvest there and have helped to drive up worldwide wheat prices.⏎The floods in Pakistan also have destroyed the logistics and transportation systems that make it

  4. #4 peak

    , stream bank erosion along the Yukon River, as well as uneven management in the Yukon Flats National Wildlife Refuge. People are worried about ever-rising prices for fuels and store-bought staples, and fewer and fewer sources of wage income

  5. #5 peak

    in Peru’s lucrative mining sector, a move that was opposed by some environmental groups. However, in 2015, mining investment fell as global commodity prices remained low and social conflicts plagued the sector.⏎Peru's free trade policy continued

  6. #6 peak

    and volatile food prices. These factors compromise responses to climate changes – both ‘normal’ variation and shocks

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 am not sure that I would like to see a lot of things." So the first step is to place the object on a surface, and the first step is to place a single object on a surface, so the next step is

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

    to something more complicated like a house that is bought, or a lawyer that is hired. You need to know how to count money to guard yourself against being shortchanged. Being able to properly count money is also important due to it being the basis

  2. #2 peak

    welfare state is socialistic in nature. It is based on the principles of equality and is keen to provide equal opportunity to all. It also aims to ensure equitable distribution of wealth.⏎3.It exercises control over all the economic activities. In a welfare

  3. #3 peak

    pecoupé, toupée⏎What do you find interesting about this word or phrase?⏎Comments that don't adhere to our Community Guidelines may be moderated or removed.<|endoftext|>Why travel to Europe to see old ruins when you have some fantastic ones

  4. #4 peak

    of people gathered for the event. Corner lots sold as high as $1,250.00, and “inside” lots were sold as high as $1000.00. Within four months, these men

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. L9:2912 suppresses
  2. L9:2255 suppresses
  3. L8:2346 suppresses
  4. L6:2256 excites
  5. L7:1774 weakly excites
  6. L8:2478 weakly suppresses
  7. L5:1202 weakly excites
  8. L7:2346 weakly excites
  9. L4:1077 weakly suppresses
  10. L3:1346 weakly suppresses
  11. L5:1562 weakly suppresses
  12. L9:2538 weakly suppresses
  13. L4:898 weakly suppresses
  14. L7:2239 weakly suppresses
  15. L9:569 weakly suppresses
  16. L5:1129 weakly excites
  17. L9:1460 weakly excites
  18. L2:1655 weakly suppresses
  19. L6:1564 weakly excites
  20. L1:2397 weakly suppresses
  21. L4:1816 weakly suppresses
  22. L7:1612 weakly suppresses
  23. L2:2800 weakly excites
  24. L9:2836 weakly suppresses

Feeds later layers

  1. L11:423 excites
  2. L19:2725 excites
  3. L11:587 excites
  4. L24:1015 excites
  5. L21:2044 excites
  6. L20:2489 excites
  7. L16:1384 excites
  8. L19:2333 excites
  9. L19:759 excites
  10. L17:2422 excites
  11. L22:408 excites
  12. L13:2796 excites
  13. L14:1171 excites
  14. L20:1722 excites
  15. L20:409 suppresses
  16. L12:1909 weakly excites
  17. L15:2098 weakly excites
  18. L17:1437 weakly excites
  19. L20:1411 weakly excites
  20. L20:1617 weakly excites
  21. L23:2134 weakly excites
  22. L24:2293 weakly excites
  23. L16:1367 weakly excites
  24. L25:1627 weakly 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.

2 values between -1.15 and -1.041 values between -0.94 and -0.841 values between -0.84 and -0.734 values between -0.73 and -0.635 values between -0.63 and -0.5333 values between -0.53 and -0.4291 values between -0.42 and -0.32200 values between -0.32 and -0.22550 values between -0.22 and -0.12914 values between -0.12 and -0.011126 values between -0.01 and 0.09609 values between 0.09 and 0.19249 values between 0.19 and 0.3062 values between 0.30 and 0.4026 values between 0.40 and 0.508 values between 0.50 and 0.615 values between 0.61 and 0.718 values between 0.71 and 0.813 values between 0.81 and 0.912 values between 1.02 and 1.123 values between 1.12 and 1.222 values between 1.22 and 1.331 values between 1.64 and 1.741 values between 1.74 and 1.841 values between 1.94 and 2.051 values between 2.87 and 2.97offnegativepositiveoften

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. supply
  2. _supply
  3. 供应
  4. Supply
  5. supply
  6. shortages
  7. mon
  8. supplies
  9. ius
  10. sup

Suppresses

  1. erotica
  2. TRIES
  3. aptcha
  4. endforeach
  5. etros
  6. tement
  7. ceremonial
  8. 欧式
  9. Tart
  10. voyeur