© 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. 15335
    Prev
    Next
    INDEX
    Explanations

    say oil

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

    No Comments

    Negative Logits
    ignite
    -16.38
    涿
    -15.81
    rc
    -15.75
    ATAR
    -15.56
    alten
    -15.56
     FetchType
    -15.38
     Deutschland
    -15.31
    gem
    -15.31
    agna
    -15.25
    UNCT
    -15.25
    POSITIVE LOGITS
     bedding
    12.94
    好运
    12.69
    dic
    12.44
    cion
    12.38
     figures
    12.25
    .setLayout
    12.06
     Figures
    11.88
     aver
    11.81
     besides
    11.75
    =headers
    11.75
    Activations Density 0.106%

    No Known Activations