© 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. 19388
    Prev
    Next
    INDEX
    Explanations

    selected filmography

    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
    agne
    -0.08
     Stevenson
    -0.07
    åĽ¢éĺŁåIJĪä½ľç²¾ç¥ŀ
    -0.07
    arians
    -0.07
    ourn
    -0.07
    ahr
    -0.07
    _SERIAL
    -0.07
    xFFF
    -0.07
    encil
    -0.06
    oru
    -0.06
    POSITIVE LOGITS
    iced
    0.08
    å±¥è¡ĮèģĮè´£
    0.07
    userdata
    0.07
    æĭ¬
    0.07
    Ù°
    0.06
    asih
    0.06
    缴æİ¥ä»İ
    0.06
    дам
    0.06
    ä¸įèĥľæķ°
    0.06
    uhe
    0.06
    Activations Density 0.011%

    No Known Activations