© 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. 14140
    Prev
    Next
    INDEX
    Explanations

    [权] => [权]

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

    No Comments

    Negative Logits
    templates
    -19.75
    cape
    -18.38
     template
    -18.13
    油价
    -18.00
     petrol
    -17.50
     modelling
    -17.38
    temps
    -17.38
     templ
    -17.38
     flavour
    -17.13
     jewellery
    -16.88
    POSITIVE LOGITS
    权
    19.88
    .Subject
    17.25
     Subjects
    16.88
     subject
    16.50
     subjects
    16.38
     SUBJECT
    16.25
    Subjects
    16.25
    Subject
    16.13
    сти
    15.81
    范围
    15.81
    Activations Density 0.375%

    No Known Activations