© 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. 46552
    Prev
    Next
    INDEX
    Explanations

    digits in timestamps or dates

    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
    §
    -0.07
     My
    -0.06
    èµ·
    -0.06
    Ø°ÙĬ
    -0.06
    inz
    -0.06
    -0.06
    ìĿ´íĦ°
    -0.06
    äºĭæĪIJ
    -0.06
    æľīæĦŁ
    -0.06
     MVP
    -0.06
    POSITIVE LOGITS
     currentPage
    0.08
    iefert
    0.08
    ingly
    0.08
    ä¸Ģæĭį
    0.07
    _simps
    0.07
    æ»ĵ
    0.07
    oring
    0.07
    aip
    0.07
    /providers
    0.07
    CharArray
    0.07
    Activations Density 0.008%

    No Known Activations