© 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. 419
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    odd
    -0.11
     Shrine
    -0.11
    _tpl
    -0.10
    arp
    -0.10
    alue
    -0.09
    raq
    -0.09
    achat
    -0.09
    nex
    -0.09
     Division
    -0.09
    etur
    -0.09
    865
    -0.09
    ysa
    -0.09
    393
    -0.09
    jíž
    -0.09
    shr
    -0.09
    257
    -0.09
    nitř
    -0.08
    축
    -0.08
    allas
    -0.08
     Py
    -0.08
    Positive Logits
    aded
    0.13
    osen
    0.12
    ramer
    0.10
     bure
    0.10
     Boyle
    0.10
     Kale
    0.10
     Globe
    0.09
    -fix
    0.09
     typ
    0.09
    紀
    0.09
     �
    0.09
    setDescription
    0.09
     Wyn
    0.09
    SetColor
    0.09
    onen
    0.09
     Activ
    0.09
     vessel
    0.09
     bou
    0.09
     Lambert
    0.09
    flat
    0.08
    Activations Density 53.307%
    Loading dashboard...