© 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. 15005
    Prev
    Next
    INDEX
    Explanations

    email placeholder

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

    No Comments

    Negative Logits
    iod
    -17.75
     userDao
    -17.50
    椿
    -17.13
    jsonData
    -16.63
    篁
    -16.25
    ourg
    -16.13
    leton
    -15.94
    �
    -15.88
    orch
    -15.81
     jungle
    -15.69
    POSITIVE LOGITS
    _star
    19.50
     Francesco
    17.25
     Tweet
    17.25
     bánh
    16.88
    牵引
    16.75
    牧
    16.63
    -star
    16.63
     rover
    16.25
    谩
    16.25
     Ste
    15.94
    Activations Density 0.979%

    No Known Activations