© 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. 63522
    Prev
    Next
    INDEX
    Explanations

    dilutions and dilutions

    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
    ulet
    -0.08
    iola
    -0.08
    chaft
    -0.08
    linger
    -0.07
    prises
    -0.07
    culares
    -0.07
    euse
    -0.07
    ê¸ĪìĿĢ
    -0.07
    elek
    -0.07
    paragus
    -0.07
    POSITIVE LOGITS
    /de
    0.09
    ution
    0.09
    ç¨ĢéĩĬ
    0.08
    anda
    0.08
    ÑģÑı
    0.08
    argest
    0.08
    度çļĦ
    0.08
    ary
    0.08
    ard
    0.08
    ERENCE
    0.08
    Activations Density 0.019%

    No Known Activations