© 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. 15295
    Prev
    Next
    INDEX
    Explanations

    say Lee

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

    No Comments

    Negative Logits
    spi
    -17.13
    刀
    -17.00
    語
    -16.75
    _slices
    -16.50
    /***/
    -16.50
    anguages
    -16.38
    ода
    -16.38
    atables
    -16.25
     mother
    -16.25
    _Inter
    -16.13
    POSITIVE LOGITS
     ATTRIBUTE
    15.81
     Attr
    14.56
    Attr
    14.44
     population
    14.44
    定向
    14.13
     Sleeve
    13.81
     pó
    13.69
    决策
    13.63
     Cooke
    13.50
    policy
    13.38
    Activations Density 0.021%

    No Known Activations