© 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. 14561
    Prev
    Next
    INDEX
    Explanations

    [20] => digit

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

    No Comments

    Negative Logits
    邠
    -18.00
     spoiler
    -17.38
     Schön
    -16.13
    がら
    -15.69
     spoilers
    -15.13
    ŏ
    -14.94
     rehabilit
    -14.94
     healed
    -14.69
     virgin
    -14.00
    xad
    -13.75
    POSITIVE LOGITS
    素
    18.38
    ��
    17.25
     �
    17.25
    多
    17.00
    sl
    17.00
    重大
    16.25
    篮
    16.13
    代
    16.13
    斯
    16.00
    鼠
    15.81
    Activations Density 0.043%

    No Known Activations