© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15298
    Prev
    Next
    INDEX
    Explanations

    say colon

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

    No Comments

    Negative Logits
    olvable
    -20.00
    鞠
    -17.88
    leasing
    -17.88
     Pavel
    -16.25
    bij
    -16.25
    _Component
    -16.00
     CSL
    -15.88
    .apps
    -15.88
    erva
    -15.38
    瑾
    -15.38
    POSITIVE LOGITS
    打入
    14.88
    峒
    14.69
     Yad
    14.69
     метро
    14.25
     Gardner
    14.19
    ader
    14.00
    尼亚
    14.00
     Kah
    13.88
    äh
    13.81
    iaz
    13.50
    Activations Density 0.032%

    No Known Activations