© 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. 470
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     inst
    -0.12
    indr
    -0.11
     ges
    -0.11
     Giang
    -0.10
    /boot
    -0.10
     democr
    -0.10
     mage
    -0.10
    paren
    -0.10
     ins
    -0.10
    elps
    -0.09
     Balk
    -0.09
    .Modules
    -0.09
     Hub
    -0.09
     ramps
    -0.09
     overs
    -0.09
     �
    -0.09
    imb
    -0.09
    PELL
    -0.09
    ottle
    -0.09
    enti
    -0.09
    Positive Logits
    ольно
    0.11
     PIT
    0.10
    coop
    0.10
    ukan
    0.10
    vc
    0.09
    BP
    0.09
    ่าวว
    0.09
    elly
    0.09
    265
    0.09
    /runtime
    0.09
     Doming
    0.09
    atte
    0.09
    itta
    0.09
     unfinished
    0.09
    063
    0.09
     griev
    0.09
     Huffington
    0.09
     su
    0.08
    rend
    0.08
     twe
    0.08
    Activations Density 43.467%
    Loading dashboard...