© 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. Llama3.3-70B-IT
    5. MLP Neurons - Layer 21
    7. 304
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     lion
    -0.11
    řád
    -0.10
     Burr
    -0.10
    _numpy
    -0.10
    etched
    -0.10
    ruk
    -0.10
    .Butter
    -0.10
    lob
    -0.10
     lest
    -0.09
     Ferguson
    -0.09
    yz
    -0.09
     赤
    -0.09
    -last
    -0.09
    ยง
    -0.09
     Fres
    -0.09
     Otto
    -0.09
     Albert
    -0.09
     Bik
    -0.09
    otic
    -0.09
    QueryBuilder
    -0.09
    Positive Logits
    elves
    0.11
     Bash
    0.10
    bson
    0.10
    acin
    0.09
    　イ
    0.09
    kea
    0.09
     Caps
    0.09
    ording
    0.09
     Fell
    0.09
     Dimit
    0.09
     Handles
    0.09
    ahl
    0.09
    /sbin
    0.09
    량
    0.09
    ored
    0.08
     Flexible
    0.08
    uell
    0.08
     Emanuel
    0.08
    yte
    0.08
    洲
    0.08
    Activations Density 58.608%
    Loading dashboard...