© 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. 64145
    Prev
    Next
    INDEX
    Explanations

    sequence of numbers and symbols

    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
    .nasa
    -0.07
    inho
    -0.07
     celu
    -0.07
    cich
    -0.07
    è¾Ľè¾Ľèĭ¦
    -0.07
    ussen
    -0.07
    .complete
    -0.07
    mue
    -0.07
    imbau
    -0.07
    ecca
    -0.07
    POSITIVE LOGITS
    reak
    0.07
    æĹłèĻij
    0.07
    utter
    0.07
    æıĥ
    0.07
    วà¸Ķ
    0.07
    åIJij社ä¼ļ
    0.06
    åľ°åIJij
    0.06
    _IOC
    0.06
    unting
    0.06
    thren
    0.06
    Activations Density 0.018%

    No Known Activations