© 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. 509
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    iferay
    -0.12
     Sherlock
    -0.11
    PHONE
    -0.09
    avana
    -0.09
    eled
    -0.09
     Punk
    -0.09
     perennial
    -0.09
     Cyril
    -0.09
    ünd
    -0.09
    ppv
    -0.09
    OI
    -0.09
     alien
    -0.09
    odb
    -0.09
    osta
    -0.08
     sigh
    -0.08
     Spike
    -0.08
    iji
    -0.08
     bad
    -0.08
     dive
    -0.08
     Mex
    -0.08
    Positive Logits
    因此
    0.17
     therefore
    0.14
     इसल
    0.12
     thanks
    0.11
    halb
    0.11
     поэтому
    0.11
     because
    0.11
     dafür
    0.11
     accordingly
    0.11
    |:
    0.10
     потому
    0.10
     благодаря
    0.10
     result
    0.10
     quindi
    0.10
    isto
    0.10
    emos
    0.10
     Masc
    0.10
     damit
    0.10
    ysi
    0.10
    ため
    0.10
    Activations Density 57.768%
    Loading dashboard...