© 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. 14199
    Prev
    Next
    INDEX
    Explanations

    no clear association

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

    No Comments

    Negative Logits
    骀
    -16.88
    แพ
    -16.88
     sequences
    -16.38
     Satisfaction
    -16.38
    destruct
    -16.13
    ieux
    -16.00
    _vel
    -15.94
    序列
    -15.50
     Structures
    -15.44
    孺
    -15.38
    POSITIVE LOGITS
    ynos
    16.75
    TRS
    16.38
    assoc
    15.13
     mixed
    14.81
    混合
    14.63
    mixed
    14.56
    associ
    14.31
     Cummings
    14.19
    panels
    14.19
    Associ
    14.13
    Activations Density 0.491%

    No Known Activations