© 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. 14673
    Prev
    Next
    INDEX
    Explanations

    filter terms

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

    No Comments

    Negative Logits
     capt
    -15.63
    avenport
    -15.38
    felt
    -15.38
    cá
    -15.00
    \Database
    -15.00
    unik
    -14.94
     günlük
    -14.94
    holm
    -14.94
    �
    -14.75
    阅读全文
    -14.75
    POSITIVE LOGITS
    edef
    15.44
    /map
    13.31
     {?
    13.13
    掖
    12.75
     SCAN
    12.63
    惭
    12.44
    odos
    11.94
    (rotation
    11.88
    创建工作
    11.88
    Rotation
    11.50
    Activations Density 0.070%

    No Known Activations