© 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. 12462
    Prev
    Next
    INDEX
    Explanations

    journal citations

    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
    lieg
    -0.08
    oga
    -0.08
    :{}
    -0.07
     Utre
    -0.07
    borough
    -0.07
    ç«ĭ
    -0.07
    amaz
    -0.07
    ATTERN
    -0.07
    imentary
    -0.07
    endencies
    -0.07
    POSITIVE LOGITS
     sauf
    0.07
    istr
    0.07
    pear
    0.07
    .obtain
    0.06
     phẩm
    0.06
    飦å°Ķ
    0.06
    æµ·éģĵ
    0.06
    avant
    0.06
     дело
    0.06
    estring
    0.06
    Activations Density 0.013%

    No Known Activations