© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62887
    Prev
    Next
    INDEX
    Explanations

    super-wide-angle, one-dimensional, semi-professional, next-to-leading, giant multilamellar vesicle, early-bird, subcompact crossover, quasi contact head

    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
    heen
    -0.09
    å·įå·į
    -0.07
    elyn
    -0.07
    æĬĺä¸įæī£
    -0.06
    åĴĮæĦıä¹ī
    -0.06
    è¿
    -0.06
    lesi
    -0.06
    npos
    -0.06
    ÉĻdÉĻ
    -0.06
    ABLE
    -0.06
    POSITIVE LOGITS
    idor
    0.08
    itarian
    0.07
    è¿ŀäºij
    0.07
    ooter
    0.07
    ular
    0.07
    andom
    0.07
    漿
    0.07
    atra
    0.07
    varo
    0.07
    lapping
    0.07
    Activations Density 0.465%

    No Known Activations