© 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. 64555
    Prev
    Next
    INDEX
    Explanations

    oil, alpha, hash

    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
    tui
    -0.07
    enheim
    -0.07
    ardon
    -0.07
    nat
    -0.06
     rut
    -0.06
    met
    -0.06
    vall
    -0.06
    mpp
    -0.06
    itado
    -0.06
    iren
    -0.06
    POSITIVE LOGITS
    unas
    0.08
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.08
     already
    0.08
    è¦ģåIJij
    0.07
    zzi
    0.07
    кок
    0.07
    amna
    0.07
    oin
    0.07
    alas
    0.07
    çĴŀ
    0.07
    Activations Density 0.384%

    No Known Activations