© 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. 46495
    Prev
    Next
    INDEX
    Explanations

    micropump, semiconductor laser, cast shadows, drive motor, melanoma, engagement ring, Florida panthers, American Football, house mice, bone screws

    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
    å¼ı设计
    -0.06
    ве
    -0.06
    åħ¨éĥ¨åĨħ容
    -0.06
    à°¤à±ģ
    -0.06
    ä¸ľè¥¿
    -0.06
    åĴĮ使åij½
    -0.06
    baum
    -0.06
    iban
    -0.05
    è¡¥çŁŃæĿ¿
    -0.05
    ANTA
    -0.05
    POSITIVE LOGITS
    UEST
    0.08
    أس
    0.08
    -readable
    0.08
    [op
    0.07
    /Private
    0.07
    /etc
    0.07
    שר
    0.07
    æľ¬ç¯ĩ
    0.07
    ارÛĮ
    0.07
    کت
    0.07
    Activations Density 0.169%

    No Known Activations