© 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. 487
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ambre
    -0.12
    .mybatisplus
    -0.12
    bris
    -0.11
    axter
    -0.11
    ikon
    -0.10
    bsite
    -0.10
     очередь
    -0.10
     Rein
    -0.10
    aigned
    -0.10
    urdu
    -0.10
    REEN
    -0.10
    ержав
    -0.10
     ゝ
    -0.10
    tif
    -0.10
    ANDLE
    -0.10
    шив
    -0.10
    hdr
    -0.10
    REA
    -0.10
     Validators
    -0.10
    AGING
    -0.09
    Positive Logits
     Vir
    0.11
    illac
    0.10
     Fletcher
    0.09
    ingly
    0.09
    �
    0.09
     CL
    0.09
    ifice
    0.09
    foot
    0.09
    avar
    0.09
     Hort
    0.08
     Kenny
    0.08
    748
    0.08
     Mil
    0.08
    ugu
    0.08
    0.08
    gh
    0.08
    aj
    0.08
    (V
    0.08
     SPE
    0.08
     Jog
    0.08
    Activations Density 46.454%
    Loading dashboard...