Neuron Explorer

Qwen3-0.6B

opening bracket in math and definitions

A neuron in layer 5 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 fires on an opening bracket '(' that introduces a definition, a formula part or a list of alternatives, such as 'vertices (or things)' or 'roots (or zeros)'. Turning it up didn't produce a clear theme in the sample text.

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

    industry are able to sell,” the report said.<|endoftext|>Determining if a Product is Positive or Negative⏎Recall the following properties of multiplication of signed numbers:⏎(positive)(positive) = positive⏎(positive)(negative) = negative⏎(n

  2. #2 peak

    "⏎- S: (v) displace, fire, give notice, can, dismiss, give the

  3. #3 peak

    1) and V = (- 1 , 2 , 1 ,- 1) are orthogonal vectors in R 4 . Write the vector X = (1 , 1 , 1 , 2) in the form X =

  4. #4 peak

    collaborative coding environment can be conveniently captured by a graph. The vertices (or things) are people, organizations, projects, and tickets. The edges (

  5. #5 peak

    point particle or string- particle or triangle- particle? No, Euler's formula has quantity (pi) which says me that the particle must be only a circle . Now I

  6. #6 peak

    version.View Full Document⏎Unformatted text preview: itself, and if ( ) ( ) lim lim x c x c h x L g x = = then ( ) lim x c f x exists and is equal to L. Three Special Limits

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: your family - The family In the context of Python programming, what is the purpose of this context? ** Let me try to understand this. I need to think about the Python programming language. Okay, let's see what I

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

    When, the glow of the reference matches with the hot object through an eye piece, that electric

  2. #2 peak

    ()⏎- Automatic variables left on the stack of languages like C or garbage collected in languages like Java.⏎Byers, Simon. Scalable Exploitation of, and Responses to Information Leakage Through Hidden Data in Published Documents, AT&T Research, April

  3. #3 peak

    finding leaks that would otherwise be hard to detect by direct observation of methane concentrations in the air.⏎This project is developing remote sensing methods of detecting, discriminating, and mapping the effects of natural gas leaks from underground pipelines. The current focus is on

  4. #4 peak

    the lender will be assessing the borrower's ability to repay the loan based on a worst-case scenario interest rate. The calculation for individuals with irregular income may be different from those

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. L3:276 excites
  2. L2:1684 weakly suppresses
  3. L3:182 weakly suppresses
  4. L4:542 weakly excites
  5. L3:1820 weakly suppresses
  6. L1:282 weakly excites
  7. L3:353 weakly suppresses
  8. L1:2078 weakly excites
  9. L4:1493 weakly suppresses
  10. L4:493 weakly suppresses
  11. L0:2626 weakly excites
  12. L4:458 weakly suppresses
  13. L1:1676 weakly excites
  14. L4:859 weakly excites
  15. L1:132 weakly excites
  16. L3:378 weakly excites
  17. L2:2124 weakly suppresses
  18. L4:2860 weakly suppresses
  19. L3:76 weakly suppresses
  20. L4:896 weakly suppresses
  21. L4:2145 weakly excites
  22. L0:440 weakly suppresses
  23. L2:559 weakly excites
  24. L3:37 weakly excites

Feeds later layers

  1. L12:1502 excites
  2. L6:144 excites
  3. L11:2191 excites unclear: brackets and parentheses in text
  4. L26:2195 weakly suppresses
  5. L6:1462 weakly excites
  6. L16:1967 weakly excites
  7. L24:848 weakly suppresses
  8. L7:795 weakly excites
  9. L15:2516 weakly excites
  10. L21:1628 weakly suppresses
  11. L9:796 weakly excites
  12. L6:2078 weakly suppresses
  13. L10:784 weakly excites
  14. L8:2184 weakly excites
  15. L14:3050 weakly suppresses
  16. L12:1287 weakly excites
  17. L11:1361 weakly excites
  18. L22:803 weakly suppresses
  19. L15:1517 weakly excites
  20. L6:323 weakly suppresses
  21. L26:1 weakly suppresses
  22. L25:947 weakly suppresses
  23. L7:2630 weakly suppresses
  24. L17:1004 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 -0.82 and -0.782 values between -0.78 and -0.743 values between -0.74 and -0.705 values between -0.70 and -0.671 values between -0.67 and -0.632 values between -0.63 and -0.591 values between -0.59 and -0.552 values between -0.51 and -0.472 values between -0.47 and -0.435 values between -0.43 and -0.398 values between -0.39 and -0.3514 values between -0.35 and -0.3123 values between -0.31 and -0.2764 values between -0.27 and -0.23106 values between -0.23 and -0.19200 values between -0.19 and -0.15364 values between -0.15 and -0.11485 values between -0.11 and -0.07612 values between -0.07 and -0.03703 values between -0.03 and 0.01474 values between 0.01 and 0.05345 values between 0.05 and 0.09243 values between 0.09 and 0.13114 values between 0.13 and 0.1776 values between 0.17 and 0.2132 values between 0.21 and 0.2512 values between 0.25 and 0.294 values between 0.29 and 0.331 values between 0.33 and 0.372 values between 0.61 and 0.651 values between 0.69 and 0.731 values between 0.73 and 0.77offnegativepositiveoften

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. atsu
  2. ochond
  3. utan
  4. AffineTransform
  5. agen
  6. 也应该
  7. ზ
  8. 填补
  9. ually
  10. b

Suppresses

  1. quier
  2. éric
  3. 部分
  4. 깐
  5. igion
  6. ivity
  7. ificant
  8. heid
  9. egie
  10. 一侧