© 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. 21748
    Prev
    Next
    INDEX
    Explanations

    date, number, or quote start

    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
    转载èĩ³
    -0.08
    .xls
    -0.07
    ä¸ĢæĮĩ
    -0.07
    lieg
    -0.07
    Canonical
    -0.07
    ä¸ĭè§Ĵ
    -0.07
    olé
    -0.07
    åIJĦæĹı
    -0.07
    nico
    -0.07
    маÑħ
    -0.07
    POSITIVE LOGITS
    ushima
    0.06
    ers
    0.06
    ÃĶ
    0.06
    æ·³
    0.06
    âĢ¦âĢ¦
    0.06
    agon
    0.06
    çļĦäºĭåĬ¡
    0.06
    licit
    0.06
    ç¼´è´¹
    0.06
    �
    0.06
    Activations Density 0.022%

    No Known Activations