© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15722
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII characters

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

    No Comments

    Negative Logits
    虎
    -20.88
    Pro
    -20.63
     Pro
    -18.38
     Cla
    -18.25
    鹰
    -17.63
    pro
    -17.63
    豹
    -17.63
     sqlCommand
    -17.38
     proton
    -17.25
    CELER
    -17.25
    POSITIVE LOGITS
    .mc
    16.63
    噩
    16.38
    疮
    16.13
    ูล
    15.63
     Trash
    15.50
    韭菜
    15.44
    泗
    15.44
    匏
    15.38
    rics
    15.13
    äll
    15.13
    Activations Density 1.051%

    No Known Activations