© 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. 22888
    Prev
    Next
    INDEX
    Explanations

    is alive

    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
    erio
    -0.10
    eria
    -0.10
    Ø®ÙĬ
    -0.09
    asiun
    -0.09
    er
    -0.09
    eran
    -0.08
    inander
    -0.08
    mith
    -0.08
    erait
    -0.08
    ialis
    -0.08
    POSITIVE LOGITS
    :
    0.06
    ä¸Ŀ毫ä¸į
    0.06
    ãģ¨æĢĿãģĦãģ¾ãģĻ
    0.06
    æ§ĺåŃIJ
    0.06
    .
    0.06
    ammers
    0.06
    ãģ®ãģ§
    0.06
    uy
    0.06
    /w
    0.06
    uet
    0.06
    Activations Density 0.005%

    No Known Activations