© 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. 413
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    apa
    -0.11
    aar
    -0.11
    edo
    -0.10
    ICC
    -0.10
     Voll
    -0.10
    耳
    -0.10
    [args
    -0.10
     lit
    -0.10
     Riv
    -0.10
    zzo
    -0.10
     Gian
    -0.10
    ablish
    -0.09
    539
    -0.09
     Fur
    -0.09
    eddar
    -0.09
    ◎
    -0.09
     Amph
    -0.09
     trib
    -0.09
    baugh
    -0.09
     Ear
    -0.09
    Positive Logits
     Fatal
    0.11
     Deferred
    0.10
     deferred
    0.10
     Ratio
    0.10
     Sanct
    0.09
    ãn
    0.09
    .getComponent
    0.09
     Hardy
    0.09
    탁
    0.09
    ivr
    0.09
    Deferred
    0.09
     circum
    0.09
     gangbang
    0.09
    途
    0.09
     Dove
    0.09
    rops
    0.09
    birthdate
    0.09
     киш
    0.08
     Tide
    0.08
     ratio
    0.08
    Activations Density 59.514%
    Loading dashboard...