© 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. 331
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Sink
    -0.11
    inish
    -0.11
    Sink
    -0.10
    leanup
    -0.10
    esson
    -0.10
     fend
    -0.10
     HEL
    -0.10
    ゛
    -0.09
    bris
    -0.09
    وین
    -0.09
    úi
    -0.09
     Longitude
    -0.09
     depreci
    -0.09
    ้ง
    -0.09
    571
    -0.09
    ttp
    -0.09
     mash
    -0.09
    ouflage
    -0.09
    ,strlen
    -0.09
    ags
    -0.08
    Positive Logits
     thr
    0.10
     Hak
    0.09
    chan
    0.09
    틀
    0.09
     Dale
    0.09
     reading
    0.09
     Bernstein
    0.09
    .Manager
    0.09
     Thr
    0.09
     Morrison
    0.09
    alers
    0.09
     Vet
    0.09
    unte
    0.09
    Meter
    0.09
     ench
    0.09
    ernote
    0.09
     Torrent
    0.09
    rov
    0.09
     ー
    0.09
    .github
    0.09
    Activations Density 43.234%
    Loading dashboard...