© 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. 48892
    Prev
    Next
    INDEX
    Explanations

    winning championships and titles

    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
     divul
    -0.07
    ä¿ĬæĿ°
    -0.07
    è·Łä¸įä¸Ĭ
    -0.07
    è°ģä¼ļ
    -0.07
    æĺ¯ä¸ª
    -0.07
    åıĤå·®ä¸įé½IJ
    -0.06
     complex
    -0.06
     whose
    -0.06
    å½¢èī²
    -0.06
    åį³å°Ĩ
    -0.06
    POSITIVE LOGITS
     coveted
    0.10
     consec
    0.09
     victories
    0.09
    èį¡
    0.09
    èĢĢçľ¼çļĦ
    0.08
    çļĦæľĢ好
    0.08
    å¿ĥæĥ³äºĭæĪIJ
    0.08
     consecutive
    0.08
     elusive
    0.08
     titoli
    0.08
    Activations Density 0.557%

    No Known Activations