© 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. 58456
    Prev
    Next
    INDEX
    Explanations

    new or learning

    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
    kau
    -0.07
    دÛĮ
    -0.07
    åı¸ç©º
    -0.07
    .openg
    -0.06
    /code
    -0.06
    éķ¿å¹´
    -0.06
    hão
    -0.06
    usti
    -0.06
    è§
    -0.06
    ikal
    -0.06
    POSITIVE LOGITS
    ç¨ļå«©
    0.16
     inexperienced
    0.15
    å°ļæľª
    0.14
    è¿ĺå¤Ħäºİ
    0.14
    è¿ĺ没æľī
    0.13
    ä¸įä¹ħçļĦ
    0.13
    éĿĴ涩
    0.13
     newly
    0.13
    åĪļåĪļå¼Ģå§ĭ
    0.13
    è¿ĺæľª
    0.13
    Activations Density 0.650%

    No Known Activations