© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30179
    Prev
    Next
    INDEX
    Explanations

    code blocks with assignments or loops

    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
    ensen
    -0.08
    çī¹çļĦ
    -0.07
    ª
    -0.07
    åĪ©äºļ
    -0.07
    wali
    -0.07
    lega
    -0.06
    æīĭæı¡
    -0.06
    æĢ§éĹ®é¢ĺ
    -0.06
    heimer
    -0.06
    åĪ·
    -0.06
    POSITIVE LOGITS
    Ä©
    0.07
    说åIJ§
    0.07
    å·¥ä½ľæĺ¯
    0.07
    ä¸Ģå¤ķ
    0.07
    æľĢä¸ĵä¸ļçļĦ
    0.06
    延年
    0.06
    åIJĮæ¯Ķåĩıå°ij
    0.06
    å·¡
    0.06
    .githubusercontent
    0.06
    æŶæ¯ı
    0.06
    Activations Density 0.004%

    No Known Activations