© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14761
    Prev
    Next
    INDEX
    Explanations

    Z

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

    No Comments

    Negative Logits
    弹
    -18.88
    彈
    -18.13
    enta
    -17.63
    _DMA
    -17.63
    华尔
    -17.25
    尼克
    -17.13
    enus
    -17.13
    NIC
    -17.00
    WC
    -16.88
    ド
    -16.75
    POSITIVE LOGITS
    atif
    15.81
    fef
    14.75
    /thumb
    14.56
    谮
    14.13
    ajes
    14.06
     Tale
    14.00
     szy
    13.94
    樵
    13.75
    蚀
    13.75
    óst
    13.75
    Activations Density 0.003%

    No Known Activations