© 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. 320
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    apan
    -0.11
     fuel
    -0.10
    418
    -0.10
    adic
    -0.10
     Boutique
    -0.09
    AGR
    -0.09
    vvm
    -0.09
    vek
    -0.09
     hugged
    -0.09
     Welsh
    -0.09
     misd
    -0.09
    arat
    -0.09
    ycz
    -0.09
     Grat
    -0.09
    etro
    -0.09
    shr
    -0.09
    unfinished
    -0.09
    Cod
    -0.09
     Localization
    -0.09
    egr
    -0.09
    Positive Logits
     online
    0.14
    ору
    0.11
     FlatButton
    0.11
    ハイ
    0.11
    ="__
    0.10
     Farm
    0.10
    .sec
    0.10
    ServerError
    0.10
    仮
    0.10
    opal
    0.10
    521
    0.10
     requ
    0.10
     Kemp
    0.10
    clado
    0.10
    achinery
    0.10
    istes
    0.10
     NXT
    0.10
     Eve
    0.10
     Affero
    0.10
     EVE
    0.10
    Activations Density 55.867%
    Loading dashboard...