© 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. 49577
    Prev
    Next
    INDEX
    Explanations

    duration, time, or intervals

    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
    isle
    -0.07
    aux
    -0.07
    assis
    -0.07
    海绵
    -0.07
    éľĨ
    -0.07
    ç§ĴéĴŁ
    -0.07
    laf
    -0.07
    дав
    -0.07
     trÆ°ng
    -0.07
    éħ£
    -0.07
    POSITIVE LOGITS
    æݨ移
    0.08
    urin
    0.08
     wore
    0.08
    ä¿ĿæĮģ稳å®ļ
    0.07
    稳å®ļçļĦ
    0.07
     throughout
    0.07
    ç©©å®ļçļĦ
    0.07
    积累
    0.07
    累计
    0.07
    以æĿ¥çļĦ
    0.07
    Activations Density 0.401%

    No Known Activations