© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14296
    Prev
    Next
    INDEX
    Explanations

    say term

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

    No Comments

    Negative Logits
    投资
    -23.25
     Invest
    -23.13
     investing
    -21.88
    的投资
    -21.88
     investment
    -21.25
     invest
    -21.13
     investments
    -20.88
     Exchange
    -20.75
    交换
    -20.75
     exchange
    -20.13
    POSITIVE LOGITS
     term
    21.25
     terms
    19.38
    terms
    18.75
    term
    18.50
     Term
    18.13
    _TERM
    17.88
    Term
    17.75
    (term
    17.38
    .Term
    17.00
    _term
    16.88
    Activations Density 3.506%

    No Known Activations