© 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. 16970
    Prev
    Next
    INDEX
    Explanations

    died or passed away

    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
    åªĽ
    -0.07
    åĩºèº«çļĦ
    -0.07
    ån
    -0.07
    äºĨåįĬ天
    -0.07
    erland
    -0.06
    _VISIBLE
    -0.06
    оÑģÑģ
    -0.06
    наÑĩ
    -0.06
    å¼Ģåı£éģĵ
    -0.06
     misdemean
    -0.06
    POSITIVE LOGITS
    享年
    0.11
    临ç»Ī
    0.10
    cheiden
    0.09
    身亡
    0.09
     ÑģмеÑĢÑĤÑĮ
    0.08
    åİ»ä¸ĸ
    0.08
    ãĤĴè¿İ
    0.08
     ÅĽmier
    0.08
    æ®ī
    0.08
    æŃ»äºİ
    0.08
    Activations Density 0.281%

    No Known Activations