© 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. 2917
    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
    丕
    -17.25
    ski
    -15.88
    ブランド
    -15.81
    ice
    -15.31
    _ARR
    -15.19
    招牌
    -14.88
    ียน
    -14.81
    _patterns
    -14.63
     Covent
    -14.63
     giảng
    -14.50
    POSITIVE LOGITS
     term
    37.75
    term
    37.50
     ter
    34.00
    (term
    33.50
     Term
    33.50
    .term
    32.75
    Term
    32.50
    -term
    31.88
     TERM
    28.75
    _term
    28.38
    Activations Density 0.012%

    No Known Activations