© 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. 3888
    Prev
    Next
    INDEX
    Explanations

    numbers and citations format

    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
    ...",
    -0.07
    ´t
    -0.07
    udi
    -0.06
    MP
    -0.06
     uncomment
    -0.06
    noinspection
    -0.06
    èݱ
    -0.06
    ôr
    -0.06
     ðŁ
    -0.06
    yo
    -0.06
    POSITIVE LOGITS
    缮çŀª
    0.08
    èĢĮä¸Ĭ
    0.07
    äºĭä¸ļä¸Ĭ
    0.07
    åĪ°çĽ®åīį
    0.07
    èĢĮ对äºİ
    0.07
     lak
    0.07
    æŁ¥çľĭåħ¨æĸĩ
    0.07
    ä½Ĩæĺ¯å¯¹äºİ
    0.07
     reli
    0.07
    akin
    0.07
    Activations Density 0.321%

    No Known Activations