© 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. 11990
    Prev
    Next
    INDEX
    Explanations

    statistical testing and inference

    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
    æľ¬æ¥¼
    -0.07
    ä¸Ģåį¡éĢļ
    -0.07
    prak
    -0.07
    åIJIJè¡Ģ
    -0.07
    storage
    -0.07
    Serialize
    -0.07
     viss
    -0.07
    ivor
    -0.07
    itm
    -0.07
    _modifier
    -0.06
    POSITIVE LOGITS
    æ£ĢéªĮ
    0.11
     statistical
    0.10
    ANO
    0.09
    ç»Łè®¡åѦ
    0.09
    åĪ¤æĸŃ
    0.09
     Statistical
    0.09
     statist
    0.09
    ç»Łè®¡
    0.08
     Stat
    0.08
     statistically
    0.08
    Activations Density 0.017%

    No Known Activations