© 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. 1505
    Prev
    Next
    INDEX
    Explanations

    say nationalities

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

    No Comments

    Negative Logits
     Ireland
    -44.00
    湖北省
    -41.50
     Irish
    -41.50
    湖北
    -37.25
    爱尔兰
    -35.50
    武汉
    -31.63
    武汉市
    -31.25
    楚
    -30.25
    珞
    -27.88
     Celtic
    -27.38
    POSITIVE LOGITS
    联邦
    16.88
    亚马逊
    15.94
    _pix
    15.81
    pix
    15.75
    纳税
    15.75
    豆
    15.63
     amazon
    15.56
     JPEG
    15.50
     σ
    15.44
    索尼
    15.38
    Activations Density 0.158%

    No Known Activations