© 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. 1499
    Prev
    Next
    INDEX
    Explanations

    do not say police

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

    No Comments

    Negative Logits
     pol
    -50.00
    pol
    -48.50
    Pol
    -47.25
     police
    -46.00
     Pol
    -44.50
    _pol
    -43.75
     Police
    -43.00
     POL
    -43.00
    Police
    -41.75
     polynomial
    -40.25
    POSITIVE LOGITS
    关键词
    17.13
     Script
    16.38
     Spart
    15.88
    Script
    15.25
     Sakura
    15.06
    HttpContext
    15.06
    built
    14.56
    html
    14.50
    .HTML
    14.50
    火焰
    14.31
    Activations Density 0.057%

    No Known Activations