© 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. 42690
    Prev
    Next
    INDEX
    Explanations

    incorrectly used terms

    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
    trup
    -0.09
    çģµæ´»çļĦ
    -0.07
    isd
    -0.07
    aporte
    -0.07
    éĢļè¿ĩåIJĦç§į
    -0.07
    æłĩæĺİ
    -0.07
    æĮĿ
    -0.07
    Writes
    -0.07
    ẻ
    -0.06
    isp
    -0.06
    POSITIVE LOGITS
    没åħ³ç³»
    0.08
    ä¸įåı¯æĢķ
    0.08
    ery
    0.07
    orie
    0.07
    è¿Ļç§įçݰ象
    0.07
    hers
    0.07
    éĿĴæ¢ħ
    0.07
    åĴĮä¸į足
    0.07
    æĪĸä¸į
    0.07
    æĽ´æŃ£
    0.07
    Activations Density 0.055%

    No Known Activations