© 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. 7704
    Prev
    Next
    INDEX
    Explanations

    Honda Motors

    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
    arrant
    -0.07
    çĴ
    -0.07
    ritt
    -0.07
    éĿŀ常容æĺĵ
    -0.07
    第ä¸Ģ大
    -0.07
    é¤ĺ
    -0.06
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    -0.06
    θεν
    -0.06
    apper
    -0.06
    ãĢģãĢĮ
    -0.06
    POSITIVE LOGITS
    uez
    0.08
    baru
    0.07
    声称
    0.07
    å¾Ĺåĩºç»ĵ论
    0.07
     ÙħØ«
    0.07
    ç«Ļä¸Ĭ
    0.06
    icke
    0.06
    èĬĻ
    0.06
    cker
    0.06
    зом
    0.06
    Activations Density 0.014%

    No Known Activations