© 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. 47471
    Prev
    Next
    INDEX
    Explanations

    after, over, on, under, when

    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
    igna
    -0.07
    ajari
    -0.07
    оÑĤоÑĢ
    -0.07
     która
    -0.07
    odb
    -0.07
    upu
    -0.07
    odz
    -0.07
    æļĤ
    -0.07
    elda
    -0.07
    ết
    -0.07
    POSITIVE LOGITS
    oug
    0.08
    /by
    0.07
    ãģŀ
    0.07
    zen
    0.07
    uers
    0.06
    à§įষ
    0.06
    ÙĪÙij
    0.06
    rael
    0.06
    миÑĤ
    0.06
    è°ĵä¹ĭ
    0.06
    Activations Density 0.706%

    No Known Activations