Neuron Explorer

Qwen3-0.6B

enzyme and protein biochemistry terms

A neuron in layer 0 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 responds to scientific words about proteins and enzymes, especially "active site" and phosphorylation. Turning it up made the model drift into counting or repeated lists, which does not clearly match the topic.

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

    fry an egg, clear white ‘liquid’ changes to solid white. This is an example of denaturation.⏎- The key with an enzyme is its active site. Its active site has a shape that is complementary with

  2. #2 peak

    , which is why the bonding and interactions between the R groups of the amino acids must be correct. If the interactions are wrong, then the shape of the active site will be wrong, and so the enzyme won’t be able to bind its substrate

  3. #3 peak

    We will also develop tools for accurately measuring the location and orientation of single fluorescent probes, which will then allow us to explore the relationships between the chemistry at the active site and the dynamics of the lever arms of myosin. All of these new

  4. #4 peak

    SUMO or NEDD8). Finally, ubiquitin can also be acetylated on Lys, or phosphorylated on Ser, Thr, or Tyr residues, and each modification can dramatically alter the signaling outcome.⏎The impact of ubiqu

  5. #5 peak

    p53 signaling pathway. B. In response to intrastrand crosslinks (crosslink), ATR and its interacting partner ATRIP become activated and phosphorylated leading to the induction of several downstream pathways. Rabbit Polyclonal to APOL

  6. #6 peak

    - Search for consensus intron/exon sequences:⏎Analysis of a large number of mRNA genes has led to the identification of highly conserved consensus sequences⏎at the 5' and 3' ends of essentially all mRNA intr

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 number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of the number of

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

    development and wound healing. Hepatocyte growth factor (HGF) is the only known ligand of the MET receptor. MET is normally expressed by cells of epithelial origin, while expression of HGF is restricted to

  2. #2 peak

    without histones? Previous studies had shown that Thermoplasma gained a bacterial protein via horizontal gene transfer – the movement of genetic material between unicellular or multicellular organisms other than through reproduction. Research by Antoine Hocher in the Molecular Systems lab

  3. #3 peak

    , we describe a protocol that employs sample derived rRNA capture probes to remove rRNA from a metagenomic total RNA sample. To begin, both mosquito and microbial small and large subunit rRNA fragments are amplified from a metagenomic community

  4. #4 peak

    discussing with⏎students that methods exist to take the analysis to a higher<|endoftext|>Cells Reference Libraries⏎Paneth Cells are one of four principal cell types found in the epithelium of the small intestine; the other three are the goblet cell,

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

None: this is the first layer.

Feeds later layers

  1. L1:935 excites
  2. L1:1715 excites
  3. L19:915 excites
  4. L1:1141 excites
  5. L4:2450 excites
  6. L21:1613 excites
  7. L24:2985 excites
  8. L4:2730 excites
  9. L22:2818 excites
  10. L21:893 weakly excites
  11. L4:394 weakly suppresses
  12. L22:814 weakly excites
  13. L23:2061 weakly excites
  14. L26:1770 weakly excites
  15. L5:2820 weakly excites
  16. L9:1869 weakly excites
  17. L5:1169 weakly excites
  18. L21:3011 weakly excites
  19. L21:406 weakly excites
  20. L25:2470 weakly excites
  21. L22:2935 weakly excites
  22. L22:1474 weakly excites
  23. L20:1978 weakly excites
  24. L18:2397 weakly excites 'followed' and 'searched' after a subject

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 -0.71 and -0.672 values between -0.51 and -0.471 values between -0.47 and -0.432 values between -0.43 and -0.391 values between -0.39 and -0.358 values between -0.35 and -0.316 values between -0.31 and -0.2710 values between -0.27 and -0.2311 values between -0.23 and -0.1925 values between -0.19 and -0.1594 values between -0.15 and -0.11201 values between -0.11 and -0.07613 values between -0.07 and -0.031854 values between -0.03 and 0.02655 values between 0.02 and 0.06257 values between 0.06 and 0.10104 values between 0.10 and 0.1432 values between 0.14 and 0.1811 values between 0.18 and 0.226 values between 0.22 and 0.265 values between 0.26 and 0.301 values between 0.34 and 0.381 values between 0.38 and 0.421 values between 0.42 and 0.461 values between 0.46 and 0.501 values between 0.54 and 0.582 values between 0.74 and 0.781 values between 0.78 and 0.821 values between 0.86 and 0.90offnegativepositiveoften

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. cesso
  2. ernes
  3. ocols
  4. hazırl
  5. exon
  6. 四级
  7. abra
  8. дорож
  9. TXT
  10. 寡

Suppresses

  1. getObject
  2. uant
  3. owania
  4. azioni
  5. jets
  6. jet
  7. FieldType
  8. esian
  9. ıt
  10. 먼