© 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. 450
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    coni
    -0.11
    kee
    -0.11
    rosso
    -0.10
    �
    -0.10
    ifest
    -0.10
    держ
    -0.10
    casting
    -0.10
    فات
    -0.09
     Owen
    -0.09
     biography
    -0.09
    622
    -0.09
    GC
    -0.09
    lom
    -0.09
     Hawaiian
    -0.09
    skyt
    -0.09
    iero
    -0.09
     seed
    -0.09
     jade
    -0.09
     voluntary
    -0.09
     Cann
    -0.09
    Positive Logits
    _kv
    0.13
    allah
    0.11
     dispatch
    0.10
     rel
    0.10
    917
    0.10
    诉
    0.10
    Radians
    0.10
    CORD
    0.10
     processing
    0.10
    ATUS
    0.09
    isy
    0.09
     p
    0.09
    ungan
    0.09
    aldi
    0.09
    널
    0.09
     Sok
    0.09
    거리
    0.09
     Bloc
    0.09
    ijn
    0.09
     flux
    0.09
    Activations Density 56.624%
    Loading dashboard...