© 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. 34687
    Prev
    Next
    INDEX
    Explanations

    complementary RNA and DNA strands

    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
    积åĪĨ
    -0.07
    æľīå¿ĥ
    -0.07
    inel
    -0.07
    ç©įåĪĨ
    -0.06
     van
    -0.06
    ove
    -0.06
    ä¸įåĢ¼å¾Ĺ
    -0.06
    embe
    -0.06
    loff
    -0.06
    zell
    -0.06
    POSITIVE LOGITS
    mirror
    0.09
    鸳鸯
    0.08
    åıįåIJij
    0.08
    该çīĩ
    0.08
    éķľåĥı
    0.08
     scrambled
    0.08
    çļĦåıį
    0.08
    utzer
    0.08
    copy
    0.08
     flipped
    0.08
    Activations Density 0.003%

    No Known Activations