© 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. 60900
    Prev
    Next
    INDEX
    Explanations

    mineral extraction

    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
    éĴĪ对
    -0.07
    bridge
    -0.07
    奢
    -0.07
    AndWait
    -0.07
    æĪĸ缴æİ¥
    -0.07
    Ø®ÙĪاÙĨ
    -0.06
    ennes
    -0.06
     باب
    -0.06
    unnel
    -0.06
    æīĢæıIJä¾Ľ
    -0.06
    POSITIVE LOGITS
    à¸Ńà¸Ńà¸ģà¸Īาà¸ģ
    0.08
     extracted
    0.08
     подлежа
    0.08
    æıIJåıĸ
    0.08
     collected
    0.08
    äºĨåĽŀæĿ¥
    0.08
     extraction
    0.08
     liberated
    0.08
    为主ä½ĵçļĦ
    0.07
    ä¿ĿåŃĺåľ¨
    0.07
    Activations Density 0.085%

    No Known Activations