© 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. 490
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    883
    -0.10
     exh
    -0.10
    abox
    -0.10
     Hur
    -0.10
     disg
    -0.09
     prof
    -0.09
    (Spring
    -0.09
    heck
    -0.09
     fixed
    -0.09
    asco
    -0.09
     Ribbon
    -0.09
    Initialized
    -0.08
    .va
    -0.08
     word
    -0.08
     fix
    -0.08
    염
    -0.08
    omba
    -0.08
     LB
    -0.08
     fixing
    -0.08
    anne
    -0.08
    Positive Logits
    Statics
    0.11
     franchise
    0.10
     Anth
    0.10
    adr
    0.10
     giả
    0.09
    尘
    0.09
     Zot
    0.09
    enville
    0.09
    OTTOM
    0.09
     ├
    0.09
     Minds
    0.09
     Cec
    0.08
     Gore
    0.08
    amen
    0.08
    andin
    0.08
    unya
    0.08
    egin
    0.08
    aten
    0.08
    iquid
    0.08
     Flesh
    0.08
    Activations Density 40.680%
    Loading dashboard...