© 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. 1631
    Prev
    Next
    INDEX
    Explanations

    [any] => 遗传

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

    No Comments

    Negative Logits
    围
    -18.25
    umerator
    -15.94
    ural
    -15.00
     här
    -14.75
    圍
    -14.56
    不平衡
    -14.38
    姐妹
    -14.06
    Cc
    -14.00
    财产
    -14.00
     limp
    -13.88
    POSITIVE LOGITS
    ndx
    18.88
    pter
    16.00
    pose
    15.56
    爷
    15.56
    跖
    15.38
    溟
    15.06
     WV
    14.94
     Astros
    14.75
    clipboard
    14.75
    encode
    14.69
    Activations Density 0.010%

    No Known Activations