© 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. 15040
    Prev
    Next
    INDEX
    Explanations

    Kennedy

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

    No Comments

    Negative Logits
    aping
    -18.38
    ศาส
    -17.75
     hemisphere
    -16.13
    世界级
    -16.13
     Goblin
    -16.00
    sortBy
    -15.81
    checker
    -15.06
    ancellor
    -14.94
     Greenwood
    -14.88
     Hemisphere
    -14.56
    POSITIVE LOGITS
     email
    14.06
    ously
    13.06
    子里
    13.00
    quo
    11.88
    /email
    11.81
    _email
    11.81
     lif
    11.75
    nez
    11.75
    老公
    11.69
    nis
    11.50
    Activations Density 0.243%

    No Known Activations