Neuron Explorer

Qwen3-0.6B

"addition" after "in" ("in addition")

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 "addition" when it follows "In" or "in", as in "In addition, ...". When it was turned up, the writing got repetitive and drifted into odd loops, with no clear theme.

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

    SCDAP/RELAP5 is used for core degradation calculations and model assessment using single effect tests or integrated experiments (QUENCH, PARAMETER, ...) in addition to<|endoftext|>Nowadays, a large number of people tend to believe that hemp and

  2. #2 peak

    any installation including a single MV/LV transformer, provided that the rated power of the transformer remains below the limit fixed by the local utility supplying the installation.⏎In addition to the functional requirements the construction of both main and secondary substations shall comply with

  3. #3 peak

    create cookies for a different domain. In addition, browsers can also allow users to view and delete cookies individually.⏎Availability of more

  4. #4 peak

    of play-based pedagogies. In addition, a large majority of teaching staff is female.⏎Similar to what research has found

  5. #5 peak

    with children who have developmental delays such as Down Syndrome, Autism, ADHD and other similar conditions.⏎A number of other rehabilitation specialists may be found in some settings in addition to the three main ones listed above. Some of these are vision therapists, recreational

  6. #6 peak

    chains of linked cells. In addition, the toxin-releasing self-destruction (autolysis) typical of pneum

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 first one! So I am going to do it, the second one! So I am going to do it, the third one! So I am going to do it, the fourth one! So I am going to do it,

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

    coni Anemia pathway (FANC), as well as the p53 signaling pathway. B. In response to intrastrand crosslinks (crosslink), ATR and its interacting partner ATRIP become activated and phosphorylated leading to the induction

  2. #2 peak

    , as the PI3 kinase ATM can be triggered by phosphorylation in response to two times strand breaks in DNA (DSBs), a related PI3 kinase ATR and its own interacting partner ATRIP react to intrastrand crosslinks in DNA

  3. #3 peak

    , although hatching may take up to two to three weeks in colder climates.<|endoftext|>When It Is Good To Be Bad : Medieval Indo-Tibetan Tantric Buddhist Apologetics (PDF)⏎Antinomianism comes in

  4. #4 peak

    the point of starving or exercise even if they are underweight.⏎It’s all in the mind⏎Shrouded under the cloak of an eating disorder, anorexia nervosa has a psychological element to it. People with anorexia may

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. L2:483 weakly suppresses
  2. L2:1778 weakly suppresses
  3. L0:1224 weakly suppresses
  4. L0:178 weakly suppresses
  5. L2:2975 weakly suppresses
  6. L0:1301 weakly suppresses
  7. L2:950 weakly suppresses
  8. L2:1036 weakly excites
  9. L1:1861 weakly suppresses
  10. L2:1690 weakly excites
  11. L2:380 weakly suppresses
  12. L1:2333 weakly excites
  13. L1:2396 weakly excites
  14. L2:1494 weakly suppresses
  15. L2:2810 weakly excites
  16. L2:75 weakly suppresses
  17. L0:770 weakly excites "of" after minority, tells or news
  18. L2:1891 weakly excites
  19. L2:3046 weakly suppresses
  20. L0:2328 weakly excites
  21. L0:1669 weakly excites
  22. L1:24 weakly excites
  23. L0:2537 weakly excites
  24. L2:49 weakly suppresses

Feeds later layers

  1. L6:144 weakly suppresses
  2. L13:1610 weakly suppresses
  3. L10:1262 weakly excites
  4. L4:2771 weakly excites
  5. L17:1553 weakly excites
  6. L4:1058 weakly excites
  7. L5:952 weakly excites
  8. L4:1949 weakly excites
  9. L12:1497 weakly excites
  10. L7:933 weakly suppresses
  11. L18:3065 weakly excites
  12. L17:2158 weakly excites
  13. L7:1387 weakly excites
  14. L7:2350 weakly excites
  15. L15:2754 weakly excites
  16. L19:1382 weakly excites 'addition' in 'In addition to'
  17. L4:2117 weakly excites
  18. L26:2998 weakly suppresses
  19. L6:1901 weakly excites
  20. L8:1815 weakly excites
  21. L21:1293 weakly suppresses
  22. L6:220 weakly excites
  23. L26:2539 weakly suppresses
  24. L18:927 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.

2 values between -0.64 and -0.554 values between -0.46 and -0.3716 values between -0.37 and -0.2885 values between -0.28 and -0.19306 values between -0.19 and -0.101165 values between -0.10 and -0.011729 values between -0.01 and 0.08449 values between 0.08 and 0.17117 values between 0.17 and 0.2623 values between 0.26 and 0.354 values between 0.35 and 0.441 values between 0.44 and 0.531 values between 0.71 and 0.801 values between 0.89 and 0.981 values between 1.25 and 1.341 values between 1.52 and 1.611 values between 1.88 and 1.971 values between 2.60 and 2.701 values between 2.88 and 2.97offnegativepositiveoften

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. ign
  2. igne
  3. ernational
  4. 0
  5. 忽略
  6. %\
  7. IGN
  8. iliar
  9. itch
  10. 设计

Suppresses

  1. annes
  2. 骅
  3. ktion
  4. тся
  5. ialis
  6. äu
  7. Hera
  8. IED
  9. ��
  10. bable