© 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. 473
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Tent
    -0.11
     Tess
    -0.11
    dete
    -0.11
    stantiate
    -0.11
     Nar
    -0.11
    ison
    -0.11
    ISON
    -0.10
     Bowen
    -0.10
    aginator
    -0.10
     spat
    -0.10
     plank
    -0.10
    _Utils
    -0.10
    hic
    -0.10
    ��
    -0.10
     Twin
    -0.09
     OPERATION
    -0.09
    obraz
    -0.09
    bread
    -0.09
    encia
    -0.09
     "(\<
    -0.09
    Positive Logits
    _mtime
    0.10
     Prosper
    0.10
     Sik
    0.10
    ensch
    0.10
    ahu
    0.10
    alist
    0.09
    imi
    0.09
    inks
    0.09
    rait
    0.09
    sted
    0.09
     �
    0.09
     cour
    0.09
    :UITableView
    0.09
     histograms
    0.09
     deduct
    0.09
    jer
    0.09
    utton
    0.09
     tails
    0.09
     Brook
    0.09
    ured
    0.09
    Activations Density 50.626%
    Loading dashboard...