© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14655
    Prev
    Next
    INDEX
    Explanations

    => to

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

    No Comments

    Negative Logits
    ani
    -14.88
    oa
    -14.38
    mp
    -14.31
    iot
    -14.13
     dere
    -13.94
    egg
    -13.63
    .readString
    -13.56
    ister
    -13.50
    etch
    -13.38
    pk
    -13.38
    POSITIVE LOGITS
    lsi
    14.38
    quires
    13.88
    丛书
    13.38
    uesta
    13.25
    śli
    13.19
    供求
    13.13
     enquiry
    13.00
     Vogue
    12.94
    ivate
    12.63
    dent
    12.56
    Activations Density 0.295%

    No Known Activations