Neuron Explorer

Qwen3-0.6B

the word 'brake' and braking

A neuron in layer 23 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron lights up on the word 'brake' (and 'braking'), especially in car and machine text like brake pads, rotors and pedals. Turning it up made the model's text drift to unrelated topics like chemistry or math, so the steering results don't show the brake theme.

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

    Corvette Stingray (C2).⏎These brakes offer better stopping performance than comparable drum brakes, including resistance to "brake fade" caused by the overheating of brake components, and are

  2. #2 peak

    the brake pads as they wear, a technician must make certain that the brake rotors are within certain standards to stop the vehicle operating in a smooth and reliable

  3. #3 peak

    brakes are less effective). Unlike a drum brake, the disc brake has no self-servo effect and the braking force is always proportional to the pressure placed on the braking pedal or lever.⏎Many early implementations for automobiles located the brakes on the inboard

  4. #4 peak

    posites (including carbon, kevlar and silica), is connected to the wheel and/or the axle. To stop the wheel, friction material in the form of brake pads (mounted on a device called a brake caliper) is forced mechanically,

  5. #5 peak

    asbestos in heat resistant products like heat–resistant pads, asbestos gloves, and woven into cloth coverings and protective blankets.⏎There was extensive use of asbestos in brake pads and shoes, as well as asbestos clutch discs and linings. For mechanics

  6. #6 peak

    give the car locomotion are turned in reverse during braking turning them into generators, returning the power to the batteries to regenerate them.⏎In this system the amount of brake pedal pressure denotes how much braking power is manual versus how much electrical energy is rec

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 value of a sample (n) in the study. I have been concerned about the value of the sample (n) and the value of the sample (n) in the study. I have been concerned that the value of the sample

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

    mRNA, miRNA, and other small RNAs were extracted from specimens using TRIzol reagent. Qiagen's miScript System was used to synthesize cDNA and perform qPCR (

  2. #2 peak

    were collected for subsequent analysis8.⏎Quantification of miRNA levels in prostate tumor samples. The main steps in qPCR analysis of tumors are: Total RNA extraction, cDNA synthesis, and detection of qPCR products using miRNA-specific primers

  3. #3 peak

    the next generation of biomarkers, therapeutic agents and/or targets.⏎Methods used to investigate miRNA expression include SYBR green I dye- based as well as Taqman-probe based qPCR. If miRNAs are to be effectively used

  4. #4 peak

    technology used to take accurate rake angle measurements.⏎- Rake Angle⏎- Positive and Negative Rake Angle in End Milling⏎- Relationship Between Cutting Tool Angle, Rake Angle, and Relief Angle⏎- Problems in Conventional Rake Angle

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. L22:167 excites
  2. L10:566 excites
  3. L20:410 excites
  4. L20:1023 excites
  5. L19:1158 weakly suppresses
  6. L1:719 weakly excites
  7. L15:1854 weakly excites
  8. L10:1092 weakly suppresses
  9. L5:1735 weakly suppresses
  10. L21:851 weakly excites
  11. L22:3029 weakly excites
  12. L9:720 weakly suppresses
  13. L10:2990 weakly suppresses
  14. L21:865 weakly suppresses
  15. L21:2094 weakly excites
  16. L19:1324 weakly suppresses
  17. L21:2184 weakly excites
  18. L5:208 weakly suppresses
  19. L10:1618 weakly suppresses
  20. L18:1460 weakly suppresses
  21. L1:951 weakly excites
  22. L9:3026 weakly excites
  23. L6:2295 weakly suppresses
  24. L14:2968 weakly excites

Feeds later layers

  1. L24:2907 weakly suppresses
  2. L27:2726 weakly excites
  3. L24:1445 weakly suppresses
  4. L25:1604 weakly excites
  5. L24:2751 weakly suppresses
  6. L27:888 weakly excites
  7. L26:2763 weakly excites
  8. L25:923 weakly excites
  9. L26:667 weakly excites
  10. L24:2255 weakly suppresses
  11. L27:41 weakly excites
  12. L24:2723 weakly excites
  13. L26:1248 weakly excites
  14. L24:499 weakly suppresses
  15. L26:412 weakly excites
  16. L24:2659 weakly excites
  17. L25:1819 weakly excites
  18. L26:762 weakly excites
  19. L24:2205 weakly excites
  20. L25:3068 weakly excites
  21. L27:2217 weakly excites
  22. L24:3027 weakly excites
  23. L26:2989 weakly suppresses
  24. L25:2559 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.

1 values between -46.88 and -45.251 values between -19.20 and -17.571 values between -11.06 and -9.432 values between -9.43 and -7.804 values between -7.80 and -6.176 values between -6.17 and -4.547 values between -4.54 and -2.9237 values between -2.92 and -1.293408 values between -1.29 and 0.34350 values between 0.34 and 1.9744 values between 1.97 and 3.6014 values between 3.60 and 5.2316 values between 5.23 and 6.855 values between 6.85 and 8.482 values between 8.48 and 10.111 values between 11.74 and 13.372 values between 13.37 and 14.995 values between 14.99 and 16.622 values between 16.62 and 18.25offnegativepositiveoften

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. dryer
  2. سطين
  3. inidad
  4. bson
  5. lining
  6. ева
  7. 扶
  8. .EventArgs
  9. nes
  10. .Writer

Suppresses

  1. imenti
  2. digest
  3. olson
  4. 国王
  5. безопас
  6. guards
  7. 札
  8. 死去
  9. ipur
  10. issen