© 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. 24495
    Prev
    Next
    INDEX
    Explanations

    electric field, magnetic field

    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
    è¾¾åħĭ
    -0.07
    дÑĢе
    -0.07
    éĢ¼äºº
    -0.07
     Relations
    -0.07
    æ°¸è¿ľçļĦ
    -0.07
    å®ľ
    -0.07
    ohn
    -0.07
    æľĿ天
    -0.07
    åľ¨ä»ĬåIJİçļĦ
    -0.07
     Ersatz
    -0.07
    POSITIVE LOGITS
    æįķèİ·
    0.09
    æł·åĵģ
    0.08
    bles
    0.08
     angekommen
    0.08
    hopefully
    0.08
    åİŁçIJĨ
    0.08
    æľªçŁ¥
    0.07
    被æµĭ
    0.07
     specimen
    0.07
    åĮ¿
    0.07
    Activations Density 0.172%

    No Known Activations