© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1353
    Prev
    Next
    INDEX
    Explanations

    [Mail] => [service]

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

    No Comments

    Negative Logits
    wick
    -16.50
    经贸
    -16.00
    .isSuccess
    -16.00
    台
    -15.94
     Apt
    -15.88
    油
    -15.75
     oil
    -15.69
    电
    -15.38
    邮
    -15.19
    uos
    -15.19
    POSITIVE LOGITS
    弓
    17.88
    	ar
    17.75
    letters
    17.38
     ar
    17.38
     gluc
    17.38
    _ARCHIVE
    16.88
     archae
    16.75
     Wolf
    16.38
    archs
    16.25
    Coffee
    16.00
    Activations Density 0.231%

    No Known Activations