© 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. 64484
    Prev
    Next
    INDEX
    Explanations

    upgrade or update status

    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
    éĹ´æİ¥
    -0.07
    æĺ¯ä½łçļĦ
    -0.07
    ä½łæĺ¯æĪij
    -0.07
     indirectly
    -0.07
    arts
    -0.06
     ÙħÙħÙĨ
    -0.06
    jabi
    -0.06
     lan
    -0.06
    é»Ħé¾Ļ
    -0.06
    anggaran
    -0.06
    POSITIVE LOGITS
    ä¼ĺèī¯çļĦ
    0.07
    åѦçĶŁå¯¹
    0.07
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    /animations
    0.07
    æłĩåĩĨ为
    0.07
    çļĦæłĩåĩĨ
    0.07
    常çĶ¨çļĦ
    0.07
    æŁ¥
    0.06
    cul
    0.06
    èĩªåı¤
    0.06
    Activations Density 0.073%

    No Known Activations