© 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. 12200
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    ä¸ĢåĪĩ
    -0.07
     thất
    -0.07
    lius
    -0.06
    ÏĢο
    -0.06
     Weston
    -0.06
    cky
    -0.06
    urd
    -0.06
    iec
    -0.06
    äºĨ解详æĥħ
    -0.06
    osa
    -0.06
    POSITIVE LOGITS
    ješ
    0.08
    undred
    0.08
    å¤ĸåĬł
    0.07
    Ñĸз
    0.07
    æĪijèĩªå·±çļĦ
    0.07
     плÑİÑģ
    0.07
    мино
    0.07
    åĬłä¸Ĭ
    0.07
    illion
    0.07
    æ°´æµĴ
    0.07
    Activations Density 0.012%

    No Known Activations