© 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. 31114
    Prev
    Next
    INDEX
    Explanations

    things related to

    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
     the
    -0.09
    heids
    -0.09
    ’s
    -0.09
    ãģª
    -0.09
     sá»±
    -0.08
    éĻ
    -0.08
    ترÛĮÙĨ
    -0.08
    人å¿ĥçļĦ
    -0.08
    çļĦ人æīį
    -0.08
    _the
    -0.08
    POSITIVE LOGITS
    оÑĩно
    0.07
    åĽłä¸ºè¿ĻäºĽ
    0.07
    à¸Ń
    0.07
    à¸Ńà¸ģà¸Īาà¸ģ
    0.07
    ī
    0.07
    åĽ¾çīĩæĪĸ
    0.07
    ึà¸ģ
    0.07
    æľĢæĸ°è¯Ħ论
    0.06
    çļĦè¿Ļç§į
    0.06
    çļĦè¿ĻäºĽ
    0.06
    Activations Density 0.841%

    No Known Activations