© 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. 55431
    Prev
    Next
    INDEX
    Explanations

    passage context

    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
    iams
    -0.08
    ÏĤ
    -0.08
    ingly
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    bies
    -0.07
    -minded
    -0.07
    IMUM
    -0.07
    äºĨå¾Īå¤ļ
    -0.07
    ãģªãģĬ
    -0.07
    wania
    -0.07
    POSITIVE LOGITS
    er
    0.10
    ož
    0.09
    رة
    0.08
    à§ĩ
    0.08
    åĴĮè¡ĮåĬ¨
    0.07
    eri
    0.07
    ×Ļ
    0.07
    erÃŃa
    0.07
    ãĥ³
    0.07
    erait
    0.07
    Activations Density 0.011%

    No Known Activations