© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 991
    Prev
    Next
    INDEX
    Explanations

    say place names

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

    No Comments

    Negative Logits
     Phaser
    -17.13
     Durham
    -15.56
    ether
    -15.38
    黟
    -15.19
    醚
    -14.50
     Bowen
    -14.38
    鹈
    -14.25
    ǔ
    -14.25
    pter
    -14.13
    镇江
    -14.13
    POSITIVE LOGITS
     Swedish
    39.25
     Sweden
    34.25
    山东省
    33.75
    瑞典
    33.50
    淄
    33.50
    济南市
    33.25
     Svens
    32.25
    齐鲁
    31.38
     Stockholm
    30.13
    淄博
    29.50
    Activations Density 0.030%

    No Known Activations