© 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. 63823
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons

    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
    —if
    -0.07
    å¾Īé«ĺ
    -0.07
    imson
    -0.07
     ascend
    -0.07
    ä¸Ĭ楼
    -0.07
    еÑģÑĮ
    -0.07
    以ä¸ĬåĨħ容
    -0.07
     pricey
    -0.06
    pac
    -0.06
    bü
    -0.06
    POSITIVE LOGITS
     deeper
    0.08
    è°·åºķ
    0.07
    æľĢæ·±
    0.07
     colder
    0.07
    å¿ĥçľ¼
    0.07
     profunda
    0.07
    าล
    0.07
    æľĢæ·±çļĦ
    0.07
    ä¸ĭæĿ¥çļĦ
    0.07
    ä¸įä¸ĭåİ»
    0.07
    Activations Density 0.038%

    No Known Activations