© 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. 22505
    Prev
    Next
    INDEX
    Explanations

    programming languages and specific software

    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
    åĪĨä¹ĭ
    -0.07
    æ§Ľ
    -0.07
    RIX
    -0.07
    ãĨ
    -0.07
    ÌĢ
    -0.06
    æĿ¥èĩªç½ij绾
    -0.06
    ä¹ĭ以
    -0.06
    UCT
    -0.06
    ä¹ĭäºİ
    -0.06
    جÙĦات
    -0.06
    POSITIVE LOGITS
    ád
    0.07
    ucker
    0.07
    owski
    0.07
    ãĤīãģĹãģı
    0.06
    ãģ§ãģ¯
    0.06
    åºĶæľīçļĦ
    0.06
    ä¸Ńå¾ĹåĪ°
    0.06
    édé
    0.06
     ezen
    0.06
    èĤ¡
    0.06
    Activations Density 0.011%

    No Known Activations