© 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. 387
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     standpoint
    -0.21
    دواج
    -0.17
    /to
    -0.16
     sources
    -0.15
     kurtul
    -0.14
     angles
    -0.14
    부터
    -0.14
     perspective
    -0.14
     angle
    -0.14
    而
    -0.13
     luego
    -0.13
     vự
    -0.13
     thiện
    -0.12
    FileSync
    -0.12
    も
    -0.12
    すれば
    -0.12
     خلال
    -0.11
     scratch
    -0.11
     phía
    -0.11
    CharCode
    -0.11
    Positive Logits
    รายการ
    0.13
    ataka
    0.11
    стро
    0.10
     उसस
    0.10
     इसस
    0.10
    807
    0.10
     distant
    0.10
    くらい
    0.10
    řez
    0.09
    ระบบ
    0.09
    선
    0.09
     bundan
    0.09
    455
    0.09
    каж
    0.09
    alm
    0.09
    licer
    0.09
    รอบ
    0.09
    opr
    0.09
    をお
    0.09
    ivol
    0.08
    Activations Density 39.531%
    Loading dashboard...