© 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. 47092
    Prev
    Next
    INDEX
    Explanations

    essay writing and structure

    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
    继ç»Ń沿
    -0.08
    ugd
    -0.08
    æĹ¥å¤ľ
    -0.08
    umbuh
    -0.08
    æĬ¥åIJį人æķ°
    -0.07
    _SETUP
    -0.07
    æĪIJ为åħ¨çIJĥ
    -0.07
    arina
    -0.07
    亲身ä½ĵ
    -0.07
    æĽ´åĬłæĸ¹ä¾¿
    -0.07
    POSITIVE LOGITS
    段èIJ½
    0.10
     prose
    0.10
     content
    0.09
     paragraphs
    0.09
     plagiarism
    0.09
    åĨħ容åĴĮ
    0.09
    åĴĮåĨħ容
    0.08
    è¿ŀè´¯
    0.08
     literary
    0.08
    åĨĻä½ľ
    0.08
    Activations Density 0.030%

    No Known Activations