© 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. 65166
    Prev
    Next
    INDEX
    Explanations

    copyright or licensing information

    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
     triá»ĩt
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    icrosoft
    -0.07
    isser
    -0.07
    inkel
    -0.06
    enton
    -0.06
    为ä¸Ĭ
    -0.06
    çĥŃéŨæłĩçŃ¾
    -0.06
    éĿ¢
    -0.06
    iferay
    -0.06
    POSITIVE LOGITS
    alian
    0.08
    _MAJOR
    0.07
    osal
    0.07
    lesa
    0.07
    èį
    0.07
    çĴĭ
    0.07
    éģµå¾ª
    0.07
     abide
    0.07
    оÑģ
    0.06
    åĴĮä¸įèī¯
    0.06
    Activations Density 1.044%

    No Known Activations