© 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. 2173
    Prev
    Next
    INDEX
    Explanations

    str

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

    No Comments

    Negative Logits
     Fac
    -16.75
     Initiative
    -15.88
    reserve
    -15.31
     facet
    -15.00
    Fac
    -14.69
    定居
    -14.38
     regul
    -14.00
     Initi
    -13.69
    otyp
    -13.63
     né
    -13.56
    POSITIVE LOGITS
     str
    50.50
    (str
    47.75
    str
    46.00
    	str
    41.25
    ,str
    40.00
    [str
    38.50
    $str
    36.75
    =str
    36.50
    -str
    36.00
    .str
    35.50
    Activations Density 0.016%

    No Known Activations