© 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. 355
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    anh
    -0.12
    ANNEL
    -0.11
    /backend
    -0.11
     Gri
    -0.10
    heel
    -0.10
     quar
    -0.10
    监听页面
    -0.10
    ActionButton
    -0.09
    erton
    -0.09
     Zar
    -0.09
     Starr
    -0.09
    oom
    -0.09
     준
    -0.09
    lane
    -0.09
     AG
    -0.09
    отов
    -0.09
    İn
    -0.09
    ept
    -0.09
    ใ
    -0.09
     Sto
    -0.09
    Positive Logits
    akah
    0.10
     filib
    0.10
     profil
    0.10
    azi
    0.09
     heads
    0.09
     Mouth
    0.09
     Stout
    0.09
     �
    0.09
    profil
    0.09
    ipo
    0.09
    miss
    0.09
    verts
    0.09
     youths
    0.09
    とう
    0.09
    (水
    0.09
    .abstract
    0.09
    �
    0.09
     Caption
    0.09
     Deferred
    0.09
     Prospect
    0.09
    Activations Density 48.540%
    Loading dashboard...