© 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. 61378
    Prev
    Next
    INDEX
    Explanations

    royal titles and forms of address

    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
    ä½łçľŁ
    -0.09
    è¿Ļ家ä¼Ļ
    -0.08
    è¿Ļå°ıåŃIJ
    -0.08
    æīĽèµ·
    -0.08
    åļ·
    -0.08
    ânico
    -0.08
    çļĦå°ijå¹´
    -0.07
    æľ¬ç½ij转载
    -0.07
    ovah
    -0.07
    èv
    -0.07
    POSITIVE LOGITS
    æĤ¨çļĦ
    0.11
     respectfully
    0.10
    éĺģä¸ĭ
    0.09
     esteemed
    0.09
    äºĮä½į
    0.08
     gracious
    0.08
    è´µ
    0.08
     Mr
    0.08
    æĤ¨
    0.08
    ê»ĺìĦľ
    0.08
    Activations Density 0.286%

    No Known Activations