© 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. 17407
    Prev
    Next
    INDEX
    Explanations

    Grand Prix

    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
    çļĦ人åı£
    -0.08
    åIJĪåĶ±åĽ¢
    -0.07
    ploy
    -0.07
    åIJĪåĶ±
    -0.07
    女足
    -0.07
    é¼İ
    -0.07
    人åı£
    -0.07
    мино
    -0.07
    鸡ç¿ħ
    -0.07
    ç»Ļ对æĸ¹
    -0.07
    POSITIVE LOGITS
    enheim
    0.09
     اÙĦعاÙĦÙħ
    0.08
     Cav
    0.08
    iams
    0.07
    utine
    0.07
    icap
    0.07
     αγÏīν
    0.07
     Prix
    0.07
    æľ¬ç«Ļ
    0.07
    nuts
    0.07
    Activations Density 0.442%

    No Known Activations