© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2771
    Prev
    Next
    INDEX
    Explanations

    say subscript

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

    No Comments

    Negative Logits
     Str
    -29.50
    str
    -28.63
    Str
    -27.38
     str
    -26.88
     STR
    -26.25
    $str
    -25.88
    	str
    -25.25
    -str
    -25.25
    ,str
    -25.13
    STR
    -25.00
    POSITIVE LOGITS
     mem
    22.75
    mem
    18.88
     meth
    18.63
     mer
    17.88
    情
    17.75
     merit
    17.38
    _mem
    16.75
    meth
    16.63
     er
    16.13
    创新型
    15.63
    Activations Density 0.248%

    No Known Activations

    This feature has no known activations.