© 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. 38962
    Prev
    Next
    INDEX
    Explanations

    computational complexity or lists with values

    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
    ingan
    -0.09
    .respond
    -0.07
    dea
    -0.07
    åĪĺ家
    -0.07
    çļĦä¸Ģ天
    -0.07
    cf
    -0.06
    .addTo
    -0.06
    ÚĨÙĩ
    -0.06
    rike
    -0.06
    wert
    -0.06
    POSITIVE LOGITS
    身临åħ¶å¢ĥ
    0.07
    æľīåĪ«
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    æIJŃ
    0.07
    alla
    0.06
    utip
    0.06
    дови
    0.06
    å°ĶèĴĻ
    0.06
    æĢİ
    0.06
    Ster
    0.06
    Activations Density 0.035%

    No Known Activations