© 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. 38324
    Prev
    Next
    INDEX
    Explanations

    android platforms, citybus, ThreadLocal, & chr, Embase, output %d, omega, UniClick, gastrin

    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
    详æĥħ请
    -0.08
    éĿ¢ãģ§
    -0.08
    è¿Ļæĺ¯ä¸ª
    -0.08
    ContentSize
    -0.07
    HING
    -0.07
    æĺ¯ä¸Ģ款
    -0.07
    è¿Ļæĺ¯ä¸Ģ款
    -0.07
    ä¹ħä¹ĭ
    -0.07
    åĪĨåĪ«æĺ¯
    -0.07
    ERO
    -0.07
    POSITIVE LOGITS
     itself
    0.07
    æīĢæĭ¥æľīçļĦ
    0.06
    ewhere
    0.06
    ographique
    0.06
    âĢİ
    0.06
    åºĶçĶ¨åĪ°
    0.06
    æľ¬èº«
    0.06
    å§
    0.06
    æĦıå¤ĸçļĦ
    0.06
    ä¸Ģå¹´æĿ¥
    0.06
    Activations Density 0.222%

    No Known Activations