© 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. 64168
    Prev
    Next
    INDEX
    Explanations

    cumulative total

    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
    opt
    -0.08
    ืà¸ļ
    -0.08
    æIJģ
    -0.07
    popover
    -0.07
    ulli
    -0.07
    PROC
    -0.07
     realistic
    -0.07
    ellige
    -0.07
    è¿ŀæĹ¥æĿ¥
    -0.07
    ROOM
    -0.07
    POSITIVE LOGITS
    æŁ¿
    0.07
    umus
    0.07
     locator
    0.07
    oldt
    0.07
    Indexed
    0.06
    .middleware
    0.06
     Prive
    0.06
    è²Į
    0.06
     indire
    0.06
    -date
    0.06
    Activations Density 0.002%

    No Known Activations