Neuron Explorer

Qwen3-0.6B

bodily samples and medical tests

A neuron in layer 7 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 lights up on words for body samples and medical checks, such as blood in a stool test, stool samples, and urine. It is hard to pin down beyond that, and the words it avoids are mostly about word counts. Turning it up produced rambling text that did not clearly relate to medicine.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    copy, and fecal occult blood test.⏎- Cervical cancer: Regular Pap tests are recommended for women starting

  2. #2 peak

    2 – 19 MPN). Thereafter, FC abundance increased slightly in fall and early winter (1.9 – 24 MPN). Fecal coliform abundance during the 2000 La Niña year was much

  3. #3 peak

    a well-kept garden will yield a return ten to fifteen times greater than would the same area and location if devoted to general farm crops. A bountiful supply of vegetables close at hand where they may be secured at a few moments' notice

  4. #4 peak

    gut microbes, find out who they are and—more importantly it turns out—how they are behaving in these patients at risk for sepsis.⏎They surveyed stool samples from 14 patients with long ICU stays, including six people who stayed

  5. #5 peak

    for vitamin B12 deficiency, its clinical manifestations and⏎the possible repercussions for Australia’s refugee population.⏎Full blood count and blood film, iron studies and haemoglobinopathy studies are⏎routinely performed for newly arrived refugees in Australia.

  6. #6 peak

    610 mg of Sodium in this food.⏎Vitamins - This food has both Vitamin A and Vitamin C. One serving contains 500 International Units of Vitamin A and 1.2 mg of Vitamin C.<|endoftext|>A twig

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 number of people who like the number 15, the number of people who like the number 25, and so on, and so on, and so on... and so on... and so on... But I don't

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

    . You can export a word list with a word frequency count to import into other visualization tools. http://www.antlab.sci.w

  2. #2 peak

    want to investigate, choose your scale of measurement and enter data. Using descriptive statistics, you'll find the mean, median, mode and standard deviation, and create frequency distributions and related graphs.⏎Monday, Oct. 6, 6-8

  3. #3 peak

    frequencies next to other words, and analyze the overall theme of a text and its corpus. The following tools listed below will help you get started with building a word frequency list and using your text to visualize your data, for the most part, in

  4. #4 peak

    or two weeks, but the circumstances were stronger then us. That’s why our trip to Kazachstan was much<|endoftext|>Data mining, concordances, word frequencies, all these things can be done to analyze text and to display the results (

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. L6:2667 excites
  2. L6:683 suppresses
  3. L6:920 suppresses
  4. L6:1212 suppresses
  5. L6:666 suppresses
  6. L6:922 suppresses
  7. L6:1035 suppresses
  8. L3:1808 excites
  9. L6:16 excites
  10. L6:1203 weakly suppresses
  11. L6:1320 weakly excites
  12. L6:18 weakly excites
  13. L6:1887 weakly excites
  14. L6:1976 weakly suppresses
  15. L4:2700 weakly suppresses
  16. L4:1356 weakly suppresses
  17. L6:12 weakly excites
  18. L0:1741 weakly suppresses
  19. L5:2797 weakly excites
  20. L5:912 weakly excites
  21. L6:2129 weakly suppresses
  22. L5:2003 weakly excites
  23. L6:2102 weakly excites
  24. L6:2229 weakly excites

Feeds later layers

  1. L10:2379 suppresses
  2. L10:1657 suppresses
  3. L10:2772 suppresses
  4. L10:1617 suppresses
  5. L19:1511 suppresses
  6. L21:1607 suppresses
  7. L8:3053 suppresses
  8. L8:125 excites
  9. L15:2943 excites
  10. L22:1451 suppresses
  11. L18:1739 suppresses
  12. L10:2161 suppresses
  13. L22:2489 suppresses
  14. L11:1076 weakly suppresses
  15. L19:3043 weakly excites
  16. L8:2699 weakly excites
  17. L11:159 weakly suppresses
  18. L8:2625 weakly suppresses
  19. L9:701 weakly suppresses
  20. L20:1966 weakly suppresses
  21. L12:1350 weakly excites
  22. L9:139 weakly suppresses
  23. L11:2985 weakly excites
  24. L10:127 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 -3.13 and -3.031 values between -2.12 and -2.021 values between -1.31 and -1.212 values between -1.00 and -0.903 values between -0.80 and -0.704 values between -0.70 and -0.604 values between -0.60 and -0.5010 values between -0.50 and -0.3951 values between -0.39 and -0.29166 values between -0.29 and -0.19592 values between -0.19 and -0.091191 values between -0.09 and 0.011101 values between 0.01 and 0.11522 values between 0.11 and 0.21177 values between 0.21 and 0.3255 values between 0.32 and 0.4212 values between 0.42 and 0.529 values between 0.52 and 0.623 values between 0.72 and 0.823 values between 0.82 and 0.92offnegativepositiveoften

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. 代办
  2. 箍
  3. 盾
  4. y
  5. yclic
  6. travellers
  7. ตรวจ
  8. mith
  9. ём
  10. 움

Suppresses

  1. istributions
  2. distribution
  3. distributions
  4. -Disposition
  5. requently
  6. omial
  7. amespace
  8. изатор
  9. otypes
  10. 占有率