© 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. 61903
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    ä¸Ģç¼ķ
    -0.07
    ÑĢÑıд
    -0.07
    _svc
    -0.07
    arently
    -0.07
    æľŁåĴĮ
    -0.07
    itektur
    -0.07
    åįģäºĶç«ł
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    аÑĢе
    -0.07
    ectl
    -0.07
    POSITIVE LOGITS
    uÅŁt
    0.07
    oscop
    0.06
    ราษà¸İ
    0.06
    åIJij被åijĬ
    0.06
    koÅĽci
    0.06
    érito
    0.06
     retired
    0.06
    alj
    0.06
    czyk
    0.06
    oster
    0.06
    Activations Density 0.361%

    No Known Activations