© 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. 489
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ereg
    -0.10
     Brooke
    -0.09
     whenever
    -0.09
    ihar
    -0.09
     cere
    -0.09
     ／
    -0.09
     preced
    -0.09
     reporting
    -0.09
    abant
    -0.09
    ustin
    -0.09
    レス
    -0.09
     Marcel
    -0.09
     Enh
    -0.09
    ancock
    -0.09
    ance
    -0.08
     grop
    -0.08
     Uncomment
    -0.08
    _Master
    -0.08
    },{↵
    -0.08
    969
    -0.08
    Positive Logits
     Assault
    0.11
    IFS
    0.10
     Lon
    0.10
    /logging
    0.09
    _,,
    0.09
    WidgetItem
    0.09
     Clone
    0.09
    ریم
    0.09
    ifs
    0.09
     imper
    0.09
    /windows
    0.09
    引
    0.09
    択
    0.09
    idor
    0.09
    vrier
    0.09
    enk
    0.09
    fé
    0.09
    uke
    0.09
    _TI
    0.09
     setw
    0.08
    Activations Density 47.906%
    Loading dashboard...