© 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. 18224
    Prev
    Next
    INDEX
    Explanations

    numerical strings and abbreviations

    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
    enty
    -0.07
     equivalents
    -0.06
    为äºĨ满足
    -0.06
    迪
    -0.06
    ä¸ľæµ·
    -0.06
    çħ§çĿĢ
    -0.06
    ä¸įèĥ½æ»¡è¶³
    -0.06
    ãĤĴä¸Ńå¿ĥãģ«
    -0.06
    icity
    -0.06
    èĥ¡åIJĮ
    -0.06
    POSITIVE LOGITS
    inding
    0.08
    æīĢä»¥ä½ł
    0.08
    ä¿Ŀéļľ
    0.08
    veau
    0.07
    ä¸ĵä¸ļå§Ķåijĺä¼ļ
    0.07
    ause
    0.07
    ña
    0.07
    istration
    0.07
    ption
    0.07
    CONF
    0.07
    Activations Density 0.090%

    No Known Activations