© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Neuronpedia · MLP Neurons
    5. Llama3.3-70B-IT
    7. MLP Neurons - Layer 21
    9. 477
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Innoc
    -0.11
     Rim
    -0.11
     search
    -0.10
     заклад
    -0.10
     searches
    -0.10
     Finding
    -0.10
     collect
    -0.10
    agar
    -0.10
     rem
    -0.10
     Emanuel
    -0.10
     searching
    -0.10
    erno
    -0.10
     rog
    -0.10
     Cem
    -0.10
     searched
    -0.10
     �
    -0.09
    ￣｀
    -0.09
     busc
    -0.09
     Ost
    -0.09
    ieux
    -0.09
    Positive Logits
     Proud
    0.11
    sect
    0.11
    icana
    0.10
    ocator
    0.10
    abb
    0.10
     Travis
    0.10
    oly
    0.10
    occ
    0.10
    hof
    0.10
     hors
    0.10
    喜
    0.10
    openh
    0.09
    �
    0.09
    棚
    0.09
    iger
    0.09
     Sheet
    0.09
    curring
    0.09
    ame
    0.09
     Guerrero
    0.09
     practical
    0.09
    Activations Density 47.461%
    Loading dashboard...