© 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. 20529
    Prev
    Next
    INDEX
    Explanations

    qualified descriptions

    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
    ialog
    -0.07
    æ¯ıæĹ¥ä¸Ģç»ĥ
    -0.07
    à¸Ĭู
    -0.07
    immers
    -0.07
    quier
    -0.07
     Automatically
    -0.07
    åıĪæĥ³
    -0.07
     Roos
    -0.07
    天ä½ij
    -0.07
    ilhar
    -0.06
    POSITIVE LOGITS
    ä¾Ľ
    0.07
    auff
    0.07
    enco
    0.07
     pula
    0.07
    iani
    0.06
    çļĦçľ¼ç¥ŀ
    0.06
    å¥Ķ
    0.06
    codec
    0.06
    è§ĦèĮĥçļĦ
    0.06
    種é¡ŀãģ®
    0.06
    Activations Density 0.235%

    No Known Activations