© 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. 411
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    wand
    -0.11
    aga
    -0.11
    itable
    -0.10
    REAL
    -0.09
     Mercer
    -0.09
     Funny
    -0.09
    325
    -0.09
    732
    -0.09
    �
    -0.09
     Ey
    -0.09
    Merc
    -0.09
    Uno
    -0.09
     whe
    -0.09
     indefinite
    -0.08
    wer
    -0.08
    adele
    -0.08
    nga
    -0.08
    .gradle
    -0.08
     Perkins
    -0.08
    ugh
    -0.08
    Positive Logits
     Fest
    0.10
    قب
    0.10
     wife
    0.10
    locale
    0.09
     himself
    0.09
     Rosenberg
    0.09
    妻
    0.09
     Sav
    0.09
    ptime
    0.09
     trump
    0.09
    itech
    0.09
    067
    0.09
     RV
    0.09
    ismet
    0.09
     sav
    0.09
    QueryParam
    0.09
    ukan
    0.09
     prof
    0.09
     Martial
    0.09
     Sax
    0.08
    Activations Density 42.248%
    Loading dashboard...