© 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. 22158
    Prev
    Next
    INDEX
    Explanations

    bank account

    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
    ãģ®ãģĬåºĹ
    -0.08
    ÙĨÙĩا
    -0.08
    æ°´æĺ¯
    -0.08
    å¾·éŁ³
    -0.08
    åºĥåijĬãģ¯
    -0.07
    åħ¶éģĵ
    -0.07
    家æĺ¯
    -0.07
    ymax
    -0.07
    ubar
    -0.07
    Úº
    -0.07
    POSITIVE LOGITS
    -
    0.07
    éŃħåĬĽçļĦ
    0.06
    é¢ĨåŁŁä¸Ń
    0.06
    ä¸Ńæī¾åĪ°
    0.06
    ä¸Ńèİ·å¾Ĺ
    0.06
    b
    0.06
    è¿ĺæľīçļĦ
    0.06
    ä¸Ń寻æī¾
    0.06
    æľīçĿĢ
    0.06
    ä¸Ńè¿Ľè¡Į
    0.06
    Activations Density 0.013%

    No Known Activations