© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1761
    Prev
    Next
    INDEX
    Explanations

    [song] => [song]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     song
    -46.50
     Song
    -45.00
     songs
    -44.75
    歌
    -42.50
    Song
    -42.25
    歌曲
    -41.00
    歌声
    -40.00
    _song
    -39.25
    song
    -38.25
    -song
    -38.00
    POSITIVE LOGITS
    存储
    16.88
    stor
    16.50
    自由贸易
    15.56
    stores
    15.06
    Bay
    14.94
    jem
    14.75
     store
    14.69
     Stored
    14.63
    /store
    14.56
     stored
    14.31
    Activations Density 0.089%

    No Known Activations