© 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. 23541
    Prev
    Next
    INDEX
    Explanations

    wave-vector, Fourier transforms, differential equations

    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
    uida
    -0.08
    æīĵæįŀ
    -0.07
    æĺ¯å®¢æĪ·
    -0.07
    atul
    -0.07
    пÑģо
    -0.07
    otyp
    -0.07
    uel
    -0.07
    æķ°ãģ¯
    -0.07
    поле
    -0.07
    icole
    -0.06
    POSITIVE LOGITS
    è°±
    0.08
     spectrum
    0.08
    ampling
    0.08
    æķ£æŃ¥
    0.07
    angler
    0.07
    roÄį
    0.07
    _blocking
    0.07
     playground
    0.07
    é¢ijè°±
    0.07
    walk
    0.07
    Activations Density 0.007%

    No Known Activations