© 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. 2973
    Prev
    Next
    INDEX
    Explanations

    library

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

    No Comments

    Negative Logits
    唱歌
    -17.63
     Ney
    -15.69
     singing
    -15.50
    paint
    -15.44
     painting
    -15.31
     sung
    -15.13
    voice
    -14.94
     chant
    -14.75
     футбол
    -14.56
     song
    -14.50
    POSITIVE LOGITS
    库
    81.00
     library
    69.00
    庫
    66.50
     Library
    62.00
    Library
    61.00
    library
    58.25
     libraries
    58.25
     LIB
    55.75
    (library
    55.50
     lib
    55.25
    Activations Density 0.073%

    No Known Activations