© 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. 22475
    Prev
    Next
    INDEX
    Explanations

    nothing yet lacking experience

    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
    ullo
    -0.08
    uš
    -0.07
    ë¡
    -0.07
    è¦ģçļĦ
    -0.07
    brem
    -0.07
    ä¸įåºĶ该
    -0.07
    AttributeName
    -0.07
    æł¹æį®ä¸įåIJĮ
    -0.07
    kana
    -0.07
    asename
    -0.06
    POSITIVE LOGITS
     recul
    0.09
     comparisons
    0.08
    åıªçŁ¥éģĵ
    0.08
    antom
    0.08
    [-
    0.07
     unfortunately
    0.07
    ä¸į便
    0.07
    obi
    0.07
     comparative
    0.07
    çĦ¡æ³ķ
    0.07
    Activations Density 0.268%

    No Known Activations