© 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. 1927
    Prev
    Next
    INDEX
    Explanations

    say "google"

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

    No Comments

    Negative Logits
    武
    -46.50
    武装
    -29.25
    武术
    -28.88
     sword
    -26.75
    兵器
    -26.25
    武器
    -26.00
     muscle
    -25.88
    Mus
    -25.88
     weapon
    -25.75
    weapon
    -25.63
    POSITIVE LOGITS
     google
    19.13
     Google
    19.13
    google
    18.50
    alo
    18.13
    Google
    17.25
     Policies
    16.88
     Kernel
    16.38
    -google
    16.38
    政策
    16.13
    _google
    16.00
    Activations Density 0.098%

    No Known Activations