© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15209
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII characters

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

    No Comments

    Negative Logits
    XA
    -21.25
    axes
    -19.13
    xa
    -18.50
    automatic
    -18.38
    locations
    -18.00
     Suff
    -17.88
    Automatic
    -17.38
    ifestyles
    -17.38
    ubi
    -17.38
    ��
    -17.38
    POSITIVE LOGITS
     Syracuse
    12.81
     equiv
    12.56
    鞭
    12.19
     sar
    12.13
     quil
    11.81
     SIP
    11.69
    笙
    11.56
    endid
    11.38
     LGBTQ
    11.38
    /qt
    11.25
    Activations Density 0.258%

    No Known Activations