© 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. 9039
    Prev
    Next
    INDEX
    Explanations

    Me & My

    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
    大好
    -0.07
    嬢
    -0.06
    æľĢåIJĪéĢĤ
    -0.06
    æľ¬æ³ķ
    -0.06
    edia
    -0.06
    éļħ
    -0.06
    igny
    -0.06
    ewan
    -0.06
    ================================================================
    -0.06
    antt
    -0.06
    POSITIVE LOGITS
     _______,
    0.07
    аÑĤелÑĮно
    0.07
     Loft
    0.07
    èĢģ人家
    0.07
    atora
    0.07
    å·®çļĦ
    0.07
    æĢ»æ¯Ķ
    0.07
    trze
    0.07
    RenderTarget
    0.06
    PCM
    0.06
    Activations Density 0.008%

    No Known Activations