© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1250
    Prev
    Next
    INDEX
    Explanations

    say movies

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     nitrogen
    -35.75
    氮
    -32.25
     Nit
    -31.50
    Nit
    -31.13
    nit
    -29.63
     Argentina
    -23.25
     nit
    -22.75
    阿根廷
    -22.38
     IBM
    -19.75
    IBM
    -19.50
    POSITIVE LOGITS
    formula
    16.63
    影视
    16.50
    Movie
    15.94
    俳
    15.81
    Film
    15.63
    _movies
    15.44
     Film
    15.31
     movies
    15.31
     movie
    15.31
    Luke
    15.06
    Activations Density 0.082%

    No Known Activations