© 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. 19548
    Prev
    Next
    INDEX
    Explanations

    given something

    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
    为åħ¶
    -0.09
     thereof
    -0.08
    VML
    -0.07
     milen
    -0.07
    spo
    -0.07
    itest
    -0.07
    æĹłä¸º
    -0.07
    对åħ¶
    -0.07
    ä¹Ŀ寨
    -0.07
    enges
    -0.07
    POSITIVE LOGITS
     bahwa
    0.09
    çļĦæĺ¯ä¸Ģ个
    0.06
    帮åĬ©æĤ¨
    0.06
    аÑģа
    0.06
     a
    0.06
     orally
    0.06
     bahawa
    0.06
    a
    0.06
     ÐĴами
    0.06
     zun
    0.06
    Activations Density 0.001%

    No Known Activations