© 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. 63510
    Prev
    Next
    INDEX
    Explanations

    subgroups of groups

    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
    ä¸īéĢļ
    -0.08
    ÑĢÑıда
    -0.08
    à§İ
    -0.07
    eles
    -0.07
    зиÑĢа
    -0.07
    大éĻĨçļĦ
    -0.07
     grid
    -0.06
    æľīæĸĻ
    -0.06
    eiro
    -0.06
     plateau
    -0.06
    POSITIVE LOGITS
     closures
    0.07
    ä¸Ŀ毫ä¸į
    0.07
    å¸Ń
    0.07
    oren
    0.07
    unar
    0.07
    éĹŃ
    0.07
     subgroup
    0.07
     affiliated
    0.07
    ophys
    0.07
    hof
    0.07
    Activations Density 0.024%

    No Known Activations