Neuron Explorer

Qwen3-0.6B

unclear: prepositions in science prose

A neuron in layer 20 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 small connecting words like 'in', 'of' and 'into' that sit between a noun and what comes after it, mostly in biology and genetics writing. Turning it up made the model's replies drift into random topics, so it doesn't show a clear effect on meaning.

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

    more or less susceptible to disease is one of the biggest challenges in science today. Geneticists study how different genetic profiles affect how certain genes are turned on or off in different people, which could be the cause of a number of genetic disorders.⏎L

  2. #2 peak

    require a student to be familiar with a lot<|endoftext|>A selectable marker is a reporter gene introduced into a cell along with a gene insert. What this means is, the experim

  3. #3 peak

    within the last decade have allowed us to do so much more. We can now conduct whole-exome sequencing, a process that directly scrutinizes all protein coding regions of the genome, which is approximately 1 to<|endoftext|>- About LENS⏎-

  4. #4 peak

    today.⏎The human genome contains more than 20,000 protein-coding genes, which carry the instructions for proteins essential to the structure and function of our cells, tissues and organs. Some of these genes are very similar to each

  5. #5 peak

    GMO" about this. These are breeding techniques and processes that were developed *before* the idea of genetic engineering which is the biochemical creation of specific advantageous mutations in the genome of a plant. Before the advent of GMO farmers and plant breeders

  6. #6 peak

    an odd shape in the mutant mice: Their axons and dendrites are shorter and have fewer branches than those

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 have a very important variable, which is a variable that is not present on the original variable. I have a variable that is a variable that is not present on the original variable, and I have a variable that is a variable that 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

    turned out to be hundreds or thousands of variants involved in common diseases, and it was unclear what each one did. Only about 5% of the shared variants were in sections of DNA forming the template for genes.⏎“We were missing too much information

  2. #2 peak

    , coronary artery disease and bipolar disorder.⏎Based on the characteristics of the variants, and their location on the genome, they could tell whether the disease-causing traits are increasing or decreasing over time.⏎"We asked the question: When we look at human

  3. #3 peak

    determine this, so let’s take a look.⏎What Actually Is Autosomal And How Does It Work?⏎Autosomal, in simple terms, is a chromosome that can be tested to find segments of

  4. #4 peak

    000 protein-coding genes, which carry the instructions for proteins essential to the structure and function of our cells, tissues and organs. Some of these genes are very similar to each other because, as the genomes of humans and other mammals evolve

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. L10:1864 suppresses
  2. L17:958 suppresses
  3. L8:2563 excites
  4. L19:806 excites
  5. L7:2433 weakly suppresses
  6. L15:1981 weakly excites
  7. L19:1900 weakly excites
  8. L18:1624 weakly excites
  9. L9:1845 weakly excites
  10. L6:2532 weakly excites
  11. L9:2708 weakly suppresses
  12. L0:1900 weakly excites
  13. L19:2385 weakly suppresses
  14. L9:2066 weakly suppresses
  15. L19:2289 weakly excites
  16. L8:911 weakly excites
  17. L7:2660 weakly excites
  18. L19:1550 weakly suppresses
  19. L9:2732 weakly excites
  20. L5:2149 weakly suppresses
  21. L19:1926 weakly excites
  22. L19:599 weakly excites
  23. L15:737 weakly suppresses
  24. L17:941 weakly excites

Feeds later layers

  1. L25:399 suppresses
  2. L24:1469 suppresses
  3. L25:1139 suppresses
  4. L22:1297 suppresses
  5. L25:3008 weakly suppresses
  6. L25:1518 weakly suppresses
  7. L22:720 weakly suppresses
  8. L21:2858 weakly suppresses
  9. L24:416 weakly suppresses
  10. L27:2798 weakly suppresses
  11. L22:803 weakly suppresses
  12. L24:570 weakly suppresses
  13. L21:2786 weakly excites
  14. L24:2514 weakly suppresses
  15. L21:565 weakly excites
  16. L21:2885 weakly suppresses
  17. L21:401 weakly suppresses
  18. L21:1753 weakly excites
  19. L21:2137 weakly suppresses
  20. L21:1058 weakly suppresses
  21. L21:2934 weakly excites
  22. L22:2632 weakly suppresses
  23. L22:2665 weakly excites physical measurements and dimensions
  24. L21:2400 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 -5.81 and -5.512 values between -5.51 and -5.201 values between -3.99 and -3.682 values between -3.38 and -3.076 values between -3.07 and -2.776 values between -2.77 and -2.465 values between -2.46 and -2.166 values between -2.16 and -1.8612 values between -1.86 and -1.5519 values between -1.55 and -1.2545 values between -1.25 and -0.94123 values between -0.94 and -0.64438 values between -0.64 and -0.331258 values between -0.33 and -0.031613 values between -0.03 and 0.28279 values between 0.28 and 0.5841 values between 0.58 and 0.8819 values between 0.88 and 1.1910 values between 1.19 and 1.496 values between 1.49 and 1.806 values between 1.80 and 2.102 values between 2.41 and 2.713 values between 2.71 and 3.021 values between 3.02 and 3.323 values between 3.32 and 3.621 values between 6.06 and 6.36offnegativepositiveoften

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. يات
  2. odel
  3. iology
  4. emics
  5. iors
  6. UnitOfWork
  7. succ
  8. ще
  9. stances
  10. iples

Suppresses

  1. 变量
  2. variable
  3. Variable
  4. 변수
  5. variable
  6. variables
  7. Variables
  8. _variable
  9. parameter
  10. _Field