© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1218
    Prev
    Next
    INDEX
    Explanations

    [engagement] => [engagement]

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

    No Comments

    Negative Logits
     engagement
    -61.25
     Eng
    -59.50
    Eng
    -59.25
     engaging
    -57.75
     engage
    -57.50
     engaged
    -56.25
     engages
    -55.50
     Engagement
    -55.25
    eng
    -52.75
    ENG
    -51.50
    POSITIVE LOGITS
    -os
    17.75
     Os
    16.38
     Mac
    16.13
    Mac
    14.88
     mac
    14.81
    图书馆
    14.69
     microphone
    14.69
    剧
    14.38
    cin
    14.13
    _cs
    14.13
    Activations Density 0.083%

    No Known Activations