© 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. 61745
    Prev
    Next
    INDEX
    Explanations

    examples or illustrations

    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
    öder
    -0.07
    åĪĻåı¯
    -0.07
    缸åħ³éĺħ读
    -0.07
    çļĦè¿Ļä¸Ģ
    -0.07
    ReadStream
    -0.07
    ÙĬÙĦÙĩ
    -0.07
     bzw
    -0.07
    ioneer
    -0.07
    itted
    -0.07
    并åı¯
    -0.06
    POSITIVE LOGITS
    æŁIJç§į
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.08
    æŁIJ个
    0.07
    æľī人ä¼ļ
    0.07
     halnya
    0.07
    iby
    0.07
    类似äºİ
    0.07
    æŁIJäºĽ
    0.07
    æ¯Ķå¦Ĥ
    0.07
     something
    0.07
    Activations Density 0.057%

    No Known Activations