© 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. 354
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Jeh
    -0.10
     Isaac
    -0.09
    keh
    -0.09
    apore
    -0.09
    Scar
    -0.09
     quý
    -0.08
     Ung
    -0.08
    .scalablytyped
    -0.08
    àng
    -0.08
    opolitan
    -0.08
    dbName
    -0.08
     Scar
    -0.08
     Present
    -0.08
     Clo
    -0.08
    yla
    -0.08
    ansk
    -0.08
    ♪↵↵
    -0.08
     scar
    -0.08
    DirectoryName
    -0.08
     pon
    -0.08
    Positive Logits
    ABA
    0.10
    isson
    0.10
    iman
    0.09
    boo
    0.09
    ][_
    0.08
    imen
    0.08
    oner
    0.08
     boo
    0.08
    ovu
    0.08
    災
    0.08
     cid
    0.08
     peel
    0.08
     nudity
    0.08
     steadfast
    0.08
     PNG
    0.07
    ison
    0.07
     nerd
    0.07
    sh
    0.07
    quer
    0.07
    nie
    0.07
    Activations Density 53.738%
    Loading dashboard...