© 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. 471
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    umber
    -0.11
    ;;;;
    -0.10
    andler
    -0.10
     Cl
    -0.09
    acom
    -0.09
    otts
    -0.09
    ån
    -0.09
     Bol
    -0.09
    InProgress
    -0.09
    orm
    -0.09
     cap
    -0.09
    oned
    -0.09
    通り
    -0.09
    ture
    -0.09
     dri
    -0.09
    491
    -0.09
     Alexandra
    -0.09
    NotAllowed
    -0.08
    owi
    -0.08
    isse
    -0.08
    Positive Logits
    �
    0.11
    LETTE
    0.11
    ål
    0.11
    arde
    0.11
     �
    0.10
    loquent
    0.10
    reff
    0.10
    cím
    0.10
     вот
    0.10
    Brains
    0.10
    _rewrite
    0.10
     enr
    0.10
     Burns
    0.10
    loth
    0.10
    hoff
    0.10
     �
    0.10
    .characters
    0.10
     annunci
    0.10
     Recursive
    0.10
    .CreateIndex
    0.09
    Activations Density 53.155%
    Loading dashboard...