Neuron Explorer

Qwen3-0.6B

the verb 'guide' or 'navigate'

A neuron in layer 3 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 the word 'guide' (or 'navigate') when it is used as a verb meaning to lead or direct someone, as in 'use X-ray to guide the catheter'. Its output points toward predicting that word next. Turning it up did not make the writing about guiding.

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

    enroll<|endoftext|>- Choosing a selection results in a full page refresh.⏎- Press the space key then arrow keys to make a selection.⏎- Use left/right arrows to navigate the slideshow or swipe

  2. #2 peak

    success in the transition to adulthood by preparing and mapping out services for them as early as 14 years old. Below are some suggestions and resources to help you navigate the transition to adulthood for your child or teen with a developmental disability in the South

  3. #3 peak

    hopes the helicopter will eventually carry tools around the planet and guide astronauts when they arrive.⏎The rover launches in July 2020,

  4. #4 peak

    the insertion of the catheter. Once the catheter has been inserted into the arteries, our cardiologist will use an X-ray screen to guide the catheter to the blocked coronary artery. Once there, an expandable balloon

  5. #5 peak

    ), and some highlights are in Roberson (1980, 1986, 1993). The Kaufman book — Field Guide to Advanced Birding — should be in everyone's library as an immediate reference.

  6. #6 peak

    ⏎In this chapter, I outline the theories related to the core concepts of my research topic. The information I present in the conceptual framework will direct my study and guide my interpretation of data. The concepts based on my theoretical framework include values, values

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 been thinking about the same as I have been doing." So, if you think about the same as you have done, then the same as you have been. Now, the same as you have been. So, if you

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

    , as well as the symbol of a globalized world. In Bogotá in 2007, the General Chapter of the Dominican friars brought forward an analysis of the ambiguous double face of today’s globalized world: “From

  2. #2 peak

    19th. As a minor shareholder, with just enough shares to ask questions, Greenpeace has brought forward a motion calling on Statoil to withdraw its investments from the tar sands.⏎

  3. #3 peak

    in textual study of Madhva Vaisnava and other sastric works.⏎Nandinagari script is the western variety of the archaic Nagari script of northern India. Nandinagari is also found in the inscriptions

  4. #4 peak

    using the disciplinary methods passed down by his father.⏎“I have always believed that the way my parents disciplined me has

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. L2:2429 weakly suppresses
  2. L0:1912 weakly excites
  3. L2:527 weakly excites
  4. L2:1657 weakly excites
  5. L2:111 weakly suppresses
  6. L2:1891 weakly excites
  7. L0:1665 weakly excites
  8. L2:300 weakly excites
  9. L2:2999 weakly excites
  10. L0:1472 weakly excites
  11. L0:1594 weakly excites
  12. L1:249 weakly suppresses "to" after "help" plus object
  13. L1:1244 weakly suppresses "of" after "board" or "off"
  14. L2:2001 weakly excites
  15. L2:2167 weakly excites
  16. L1:61 weakly excites
  17. L1:1491 weakly suppresses 'for' after 'known' or 'renowned'
  18. L2:1953 weakly excites
  19. L2:2768 weakly excites
  20. L2:1250 weakly excites
  21. L1:491 weakly excites
  22. L2:2302 weakly suppresses
  23. L2:2464 weakly suppresses
  24. L2:75 weakly suppresses

Feeds later layers

  1. L4:1758 excites
  2. L26:2820 excites
  3. L22:2435 excites
  4. L18:1069 excites
  5. L12:2070 weakly excites
  6. L10:1460 weakly suppresses
  7. L20:1444 weakly suppresses
  8. L27:2284 weakly excites
  9. L26:2597 weakly excites
  10. L16:2168 weakly suppresses
  11. L20:1490 weakly suppresses
  12. L25:2505 weakly excites
  13. L8:2642 weakly excites
  14. L4:1406 weakly excites
  15. L25:1990 weakly excites
  16. L25:595 weakly suppresses
  17. L20:2310 weakly excites
  18. L18:2027 weakly suppresses
  19. L6:2160 weakly suppresses
  20. L23:2824 weakly excites
  21. L12:1757 weakly suppresses
  22. L4:1553 weakly excites 'to' after 'for someone' (purpose infinitive)
  23. L5:2141 weakly excites
  24. L7:2594 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 -1.09 and -0.911 values between -0.91 and -0.732 values between -0.73 and -0.557 values between -0.55 and -0.37151 values between -0.37 and -0.191604 values between -0.19 and -0.011876 values between -0.01 and 0.17248 values between 0.17 and 0.3512 values between 0.35 and 0.521 values between 0.52 and 0.702 values between 1.06 and 1.241 values between 5.18 and 5.361 values between 5.53 and 5.711 values between 5.89 and 6.07offnegativepositiveoften

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. -guide
  2. 的带领下
  3. Guides
  4. guide
  5. _guide
  6. guides
  7. guidance
  8. Guide
  9. /utility
  10. 指引

Suppresses

  1. amous
  2. iliated
  3. @$
  4. omon
  5. barrel
  6. _$
  7. res
  8. -cl
  9. hos
  10. def