© 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. 57628
    Prev
    Next
    INDEX
    Explanations

    homotopic to a proper holomorphi

    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
    apor
    -0.08
    zinho
    -0.07
    inho
    -0.07
    itters
    -0.07
    é«ĺé«ĺ
    -0.07
    åĨ½
    -0.07
    eldet
    -0.07
    nh
    -0.07
    atham
    -0.06
    нан
    -0.06
    POSITIVE LOGITS
    obie
    0.08
     equivalence
    0.08
    ä¸įä¸ĭåİ»
    0.08
    adesh
    0.08
    ivalence
    0.07
    empor
    0.07
    ssi
    0.07
    好æĥ³
    0.07
    iril
    0.07
    æľŁåĨħ
    0.07
    Activations Density 0.002%

    No Known Activations