© 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. 14724
    Prev
    Next
    INDEX
    Explanations

    UN resolutions

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

    No Comments

    Negative Logits
    //===
    -17.75
    actice
    -17.00
    桴
    -16.75
    ierge
    -16.75
    精华
    -16.63
    /self
    -16.38
    头条
    -16.38
    antine
    -16.38
    agic
    -16.13
    }//
    -16.13
    POSITIVE LOGITS
    html
    13.63
    mnt
    13.31
    Di
    12.63
    Username
    12.44
    那样的
    12.38
    Edition
    12.13
    Part
    11.94
    那时
    11.94
    裡
    11.88
    徵
    11.88
    Activations Density 0.031%

    No Known Activations