© 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. 2865
    Prev
    Next
    INDEX
    Explanations

    say 涉

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

    No Comments

    Negative Logits
     gen
    -22.50
    (gen
    -21.50
    	gen
    -20.50
    .gen
    -20.25
    Gen
    -20.25
     gén
    -20.25
    -gen
    -19.88
    gen
    -19.63
    _gen
    -19.13
    宝
    -19.00
    POSITIVE LOGITS
    涉
    33.25
    getInt
    24.63
     det
    24.50
    ints
    23.13
    Det
    23.13
    	Int
    22.50
    det
    22.25
     integ
    21.63
     Det
    21.50
    <Int
    21.50
    Activations Density 0.042%

    No Known Activations