© 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. 37932
    Prev
    Next
    INDEX
    Explanations

    how to find

    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
    çĽijæµĭç³»ç»Ł
    -0.07
    çİĩé«ĺ
    -0.07
    æķ´å¥Ĺ
    -0.07
    ssen
    -0.07
    常人
    -0.07
    æºIJèĩª
    -0.07
    ovor
    -0.07
    asca
    -0.06
    强度é«ĺ
    -0.06
    æĹ¥æŃ£å¼ı
    -0.06
    POSITIVE LOGITS
    æĩ¿
    0.08
    _INST
    0.07
    _("
    0.07
    ache
    0.07
    çļĦä¿¡æģ¯
    0.07
    æѦæŀĹ
    0.07
     :]
    0.07
     ==============================================================
    0.07
    elper
    0.07
    éĴ¦
    0.07
    Activations Density 0.037%

    No Known Activations