© 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. 15713
    Prev
    Next
    INDEX
    Explanations

    disbelief

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

    No Comments

    Negative Logits
    äd
    -21.13
    asia
    -20.75
    SPA
    -20.50
     CPL
    -20.13
    pek
    -20.00
    azar
    -20.00
     Ply
    -19.88
    _ACL
    -19.88
    orta
    -19.75
    OLA
    -19.75
    POSITIVE LOGITS
    gend
    12.38
     Schwe
    12.13
    拳头
    12.06
    gens
    11.81
     Tribune
    11.75
    共同体
    11.69
    eno
    11.56
    项目
    11.44
    inely
    11.31
    不同意
    11.25
    Activations Density 0.485%

    No Known Activations