© 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. 62776
    Prev
    Next
    INDEX
    Explanations

    Korean word `ë°©ë²ķ`

    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
    hado
    -0.07
    ares
    -0.07
    رÙĨ
    -0.06
    iges
    -0.06
    wali
    -0.06
    ä¸İçłĶ究
    -0.06
    agues
    -0.06
    hada
    -0.06
    tha
    -0.06
     nhắc
    -0.06
    POSITIVE LOGITS
    imai
    0.08
    åĭ¤åĭ¤æģ³æģ³
    0.08
    è±Ĩ
    0.08
    æ¼ĵ
    0.08
    身临åħ¶å¢ĥ
    0.07
    iper
    0.07
    æĬ¢åħĪ
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    óp
    0.07
    _FLUSH
    0.07
    Activations Density 0.142%

    No Known Activations