© 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. 2998
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    udi
    -0.07
    辦
    -0.07
    åĩ½æİĪ
    -0.07
    itti
    -0.07
    ÙĨت
    -0.06
    redi
    -0.06
    uze
    -0.06
    çī
    -0.06
    cest
    -0.06
    _FINISH
    -0.06
    POSITIVE LOGITS
    åł
    0.08
    IMENT
    0.07
    éĻµåĮº
    0.06
     ÐŁÑĢоÑģмоÑĤÑĢов
    0.06
    æľĢæĸ°æĸĩç«ł
    0.06
    欢è¿İ大家éĺħ读
    0.06
    -describedby
    0.06
    æļĹé»ij
    0.06
    IBUT
    0.06
     ↵        ↵
    0.06
    Activations Density 0.000%

    No Known Activations