© 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. 418
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     dying
    -0.12
    umba
    -0.11
    än
    -0.11
    pus
    -0.11
     Brass
    -0.10
     Fus
    -0.10
     │
    -0.10
    KNOWN
    -0.10
    edu
    -0.09
    istrovství
    -0.09
    ikon
    -0.09
    illian
    -0.09
    822
    -0.09
     pus
    -0.09
     Wellness
    -0.09
    aty
    -0.09
    ebo
    -0.09
    feld
    -0.09
    RI
    -0.09
     Tobias
    -0.08
    Positive Logits
    urum
    0.10
     darken
    0.10
    ungan
    0.10
    ples
    0.10
     wr
    0.10
    268
    0.09
    ese
    0.09
    ple
    0.09
     recomm
    0.09
    566
    0.09
    칭
    0.09
    ronic
    0.09
     Imper
    0.09
     Patterson
    0.09
     Forced
    0.09
     burg
    0.09
    oku
    0.09
    776
    0.09
    dust
    0.09
    �
    0.08
    Activations Density 53.286%
    Loading dashboard...