© 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. 47206
    Prev
    Next
    INDEX
    Explanations

    characteristic cycles / BSD license

    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
    rael
    -0.08
    åıĬ个人
    -0.08
    oblins
    -0.07
    rabbit
    -0.07
    aland
    -0.07
     Brescia
    -0.07
    æł¡çļĦ
    -0.07
    ãĥijãĥ¼ãĤ½
    -0.07
    ÑĢÑĭз
    -0.07
    åĴĮ个人
    -0.07
    POSITIVE LOGITS
    åĬłæ³ķ
    0.07
    çݯå¢ĥä¸ĭ
    0.07
    -browser
    0.07
    讳
    0.07
    ottom
    0.06
     unrelated
    0.06
     ruling
    0.06
    ulk
    0.06
    çĩ¥
    0.06
    -compatible
    0.06
    Activations Density 0.003%

    No Known Activations