© 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. 432
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     O
    -0.09
    .appspot
    -0.08
     drv
    -0.08
    ancock
    -0.08
     Vil
    -0.08
     限
    -0.07
     Alv
    -0.07
    _tpl
    -0.07
     Miner
    -0.07
     TSR
    -0.07
    ovel
    -0.07
     Nug
    -0.07
    ayment
    -0.07
    �
    -0.07
    ifest
    -0.07
     visa
    -0.07
     Stanton
    -0.07
     Holmes
    -0.07
     Payne
    -0.07
    erb
    -0.07
    Positive Logits
    -sw
    0.09
     Intelli
    0.08
     ､
    0.08
    _mex
    0.08
    ets
    0.08
    šk
    0.07
    629
    0.07
     gul
    0.07
    etroit
    0.07
    ucher
    0.07
    �
    0.07
     blankets
    0.07
    ivi
    0.07
     Spicer
    0.07
    forgettable
    0.07
    -‐
    0.07
    Flush
    0.07
     Benedict
    0.07
     Literary
    0.07
    arus
    0.07
    Activations Density 47.299%
    Loading dashboard...