© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26281
    Prev
    Next
    INDEX
    Explanations

    list items numbered 0-9

    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
    dba
    -0.08
    addock
    -0.08
    æĥħåĨµåĴĮ
    -0.07
    ä¸Ģæ³¢
    -0.07
     Belmont
    -0.07
    emarks
    -0.07
    elaar
    -0.07
    Selasa
    -0.07
    ÄįnÃŃ
    -0.07
    纨
    -0.07
    POSITIVE LOGITS
    é»
    0.07
    xffffffff
    0.06
    ä½łæĪij
    0.06
    itan
    0.06
    åİ»è¿ĩ
    0.06
    åĪĪ
    0.06
    ä¸įæĺ¯ä½ł
    0.06
     przep
    0.06
     begr
    0.06
    oppers
    0.06
    Activations Density 0.029%

    No Known Activations