© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1611
    Prev
    Next
    INDEX
    Explanations

    [Facebook] => [other]

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

    No Comments

    Negative Logits
    社交媒体
    -25.88
    _facebook
    -25.00
    -facebook
    -23.25
     Facebook
    -22.63
     facebook
    -22.25
    Facebook
    -21.88
    facebook
    -21.00
    ernet
    -19.63
    acebook
    -19.25
    social
    -18.88
    POSITIVE LOGITS
     geom
    16.50
    arden
    15.81
    zung
    15.63
     gé
    15.25
    ystone
    15.13
     stone
    14.88
    原子
    14.88
     stature
    14.44
    quet
    14.38
    元素
    14.38
    Activations Density 0.069%

    No Known Activations