© 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. 29503
    Prev
    Next
    INDEX
    Explanations

    coefficients and variables

    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
    wards
    -0.07
    eland
    -0.07
    ŀ
    -0.07
    rvine
    -0.06
    ä¼IJ
    -0.06
    rawer
    -0.06
    ä¸į离
    -0.06
    ovsky
    -0.06
    大使
    -0.06
    ENTRY
    -0.06
    POSITIVE LOGITS
    æŬ
    0.08
    ¿
    0.08
    [List
    0.07
    央
    0.07
    onomies
    0.07
    aturas
    0.07
    ä¸ĩåıĺ
    0.07
    hint
    0.07
    ograf
    0.07
    éĴ¥
    0.07
    Activations Density 0.043%

    No Known Activations