© 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. 46575
    Prev
    Next
    INDEX
    Explanations

    Hungarian singers

    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
    é¦ĸèµŀ
    -0.07
    beauftrag
    -0.07
    æĭ¼
    -0.07
    áĢĶáĢºáĢ¸
    -0.07
    _CONNECTED
    -0.07
    个èµŀ
    -0.07
    ÑĶм
    -0.07
    chwitz
    -0.07
    _RETURN
    -0.07
    ($_
    -0.07
    POSITIVE LOGITS
    cd
    0.08
     Merchant
    0.07
    è¿ĿåıįäºĨ
    0.07
    女
    0.07
    符åIJĪ
    0.07
    æ±²
    0.06
    æĴŃ
    0.06
    èĸ°
    0.06
    oren
    0.06
    éĩį大
    0.06
    Activations Density 0.063%

    No Known Activations