© 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. 38303
    Prev
    Next
    INDEX
    Explanations

    warranted because, looking from

    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
    å¤©çľ¼
    -0.08
    ëł¹
    -0.07
    ynu
    -0.07
    ythe
    -0.07
    éķ¿ç©º
    -0.07
    ambu
    -0.07
    ynos
    -0.07
    Ø¥ÙĨ
    -0.07
    äºijå³°
    -0.06
    ezu
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.09
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    0.07
     ÙĥØ°ÙĦÙĥ
    0.06
    op
    0.06
    oft
    0.06
    åIJĮæł·çļĦ
    0.06
    oled
    0.06
    ibi
    0.06
    ail
    0.06
    ad
    0.06
    Activations Density 3.098%

    No Known Activations