© 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. 352
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ／/
    -0.12
     Mond
    -0.12
    jezd
    -0.10
     unic
    -0.10
    ồ
    -0.10
     Trials
    -0.10
    erson
    -0.10
     HD
    -0.10
     ken
    -0.09
     spol
    -0.09
     Mez
    -0.09
    IVO
    -0.09
     Kun
    -0.09
     aras
    -0.09
     invers
    -0.09
    action
    -0.09
     Riverside
    -0.09
     slav
    -0.09
     glove
    -0.09
     transf
    -0.09
    Positive Logits
    itics
    0.10
    obra
    0.10
     pairs
    0.10
    GenerationStrategy
    0.10
     Kou
    0.10
    pairs
    0.10
    aign
    0.09
    亡
    0.09
    412
    0.09
    943
    0.09
     Selector
    0.09
    obsolete
    0.09
    ahir
    0.09
     Bryce
    0.09
    洞
    0.09
    弋
    0.09
    agi
    0.09
    UrlParser
    0.09
     pys
    0.09
    >NN
    0.09
    Activations Density 48.151%
    Loading dashboard...