© 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. 1235
    Prev
    Next
    INDEX
    Explanations

    another, second, additional

    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
    楼主
    -0.07
    ailer
    -0.07
    ä¹Ŀ大
    -0.07
    udur
    -0.07
    çļĦ羣æŃ£
    -0.07
    å®ŀéĻħè¡ĮåĬ¨
    -0.07
    çļĦæĸ°æĹ¶ä»£
    -0.06
    æľĢæĸ°æĽ´æĸ°
    -0.06
     Replies
    -0.06
     ÑģкоÑĢее
    -0.06
    POSITIVE LOGITS
    ilder
    0.08
    åIJĮ樣
    0.08
     altrettanto
    0.08
     nữa
    0.08
    ä¸ĢäºĽçļĦ
    0.07
    åIJĮæł·
    0.07
    esak
    0.07
    ä»Ģä¹Īéĥ½æ²¡æľī
    0.07
     afterward
    0.07
    åIJĮçŃī
    0.07
    Activations Density 0.121%

    No Known Activations