© 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. 50332
    Prev
    Next
    INDEX
    Explanations

    nationalities and countries

    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
    åħ¶æīĢ
    -0.08
    çłº
    -0.08
    rite
    -0.07
    alore
    -0.07
    ä¸Ģå®ļ
    -0.06
    alani
    -0.06
    inat
    -0.06
    alz
    -0.06
     impart
    -0.06
    å·¡è§Ĩåijĺ
    -0.06
    POSITIVE LOGITS
    -Russian
    0.09
    ows
    0.08
    åĴĮæĹ¥æľ¬
    0.08
    owned
    0.08
    -owned
    0.08
    epend
    0.08
    -built
    0.07
    -made
    0.07
    aged
    0.07
    -American
    0.07
    Activations Density 0.550%

    No Known Activations