© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60725
    Prev
    Next
    INDEX
    Explanations

    spacetime physics and quantum theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    马åĬĽ
    -0.08
    trut
    -0.07
    hoven
    -0.07
    à¹Īาย
    -0.07
    utan
    -0.07
    丹丹
    -0.07
    lig
    -0.07
    etan
    -0.07
     Miser
    -0.06
     descar
    -0.06
    POSITIVE LOGITS
     semiclassical
    0.10
    ymp
    0.08
     semiclass
    0.08
    æ³¢çļĦ
    0.08
     tunnel
    0.08
    wave
    0.07
    ä¹ĸ
    0.07
    平常å¿ĥ
    0.07
    åİĦ
    0.07
     quantum
    0.07
    Activations Density 0.008%

    No Known Activations