© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14065
    Prev
    Next
    INDEX
    Explanations

    say methods

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

    No Comments

    Negative Logits
    连接
    -34.25
     connection
    -32.75
     connections
    -32.00
     connect
    -31.13
     connecting
    -31.00
    connect
    -30.88
     connects
    -30.75
     link
    -29.50
     links
    -29.50
    connection
    -28.25
    POSITIVE LOGITS
    _methods
    16.38
    .ARR
    15.63
    审查
    15.13
     Services
    14.94
     methods
    14.69
    methods
    14.69
    ControlEvents
    14.63
     host
    14.63
     Arr
    14.44
    Methods
    14.38
    Activations Density 1.076%

    No Known Activations