© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48658
    Prev
    Next
    INDEX
    Explanations

    Clinton Global Initiative

    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
    ÑĢик
    -0.07
    æ°Ķå¾Ĺ
    -0.06
    atern
    -0.06
    æŃ£ç¾©
    -0.06
     </
    -0.06
    Å¡te
    -0.06
    ÅĽc
    -0.05
    wod
    -0.05
    æĬĢæľ¯ä¸Ĭ
    -0.05
    FI
    -0.05
    POSITIVE LOGITS
    ertz
    0.09
    æľīè¿Ļæł·çļĦ
    0.09
    oba
    0.08
    ä¹ĭäºİ
    0.08
    æľīè¿Ļ个
    0.08
    è¿Ļä¸ĢçĤ¹
    0.08
    çĸĨ
    0.07
    æĻ¨æĬ¥
    0.07
    è¿·æĥij
    0.07
    çļĦè¿Ļç§į
    0.07
    Activations Density 0.208%

    No Known Activations