© 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. 507
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Ch
    -0.11
    US
    -0.11
    г
    -0.11
    ab
    -0.10
    oui
    -0.10
    vet
    -0.10
    road
    -0.10
    COM
    -0.10
    hol
    -0.10
    na
    -0.09
    flow
    -0.09
    for
    -0.09
    „P
    -0.09
    row
    -0.09
    flag
    -0.09
    ambi
    -0.09
    Sp
    -0.09
    ✔
    -0.09
    isure
    -0.09
    я
    -0.09
    Positive Logits
    uitka
    0.11
     ho
    0.11
     Hod
    0.10
     Hamm
    0.10
    ﾑ
    0.10
     Cros
    0.10
    ODULE
    0.10
     Abb
    0.10
    ochen
    0.10
    ﾐ
    0.10
    ��
    0.10
    ォ
    0.10
    .maps
    0.10
    ."&
    0.10
    ASI
    0.10
    oret
    0.09
    iek
    0.09
    spe
    0.09
     Wass
    0.09
     Cele
    0.09
    Activations Density 49.557%
    Loading dashboard...