© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41162
    Prev
    Next
    INDEX
    Explanations

    Iran, Tehran, Persian, research

    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
     Belize
    -0.07
     Uganda
    -0.06
    è¶
    -0.06
    ð
    -0.06
    ç¶
    -0.06
    TRL
    -0.06
    èº
    -0.06
    åĬłåĭĴæ¯Ķ
    -0.06
     Florida
    -0.06
    ych
    -0.06
    POSITIVE LOGITS
    ä¼ĬæľĹ
    0.11
     Tehran
    0.10
     Iranian
    0.10
    Iran
    0.09
     Iran
    0.09
     Ä°ran
    0.09
     iran
    0.09
     Mehr
    0.08
     COPYING
    0.08
    mehr
    0.08
    Activations Density 0.223%

    No Known Activations