© 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. 62182
    Prev
    Next
    INDEX
    Explanations

    greetings and introductions

    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
    eced
    -0.07
    åIJijæĹ¥
    -0.07
    emp
    -0.07
    ++,
    -0.07
    aines
    -0.07
    éĢ®
    -0.06
    è§ģå¾Ĺ
    -0.06
    ()-
    -0.06
     \""
    -0.06
     alike
    -0.06
    POSITIVE LOGITS
    etheless
    0.08
    áss
    0.07
     commiss
    0.07
    ünstler
    0.06
    éĿĵ
    0.06
    į¨
    0.06
     REGOL
    0.06
    imbus
    0.06
    ASP
    0.06
    Ĥ¹
    0.06
    Activations Density 0.019%

    No Known Activations