© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48434
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
    udin
    -0.07
    itier
    -0.07
    å¾Īå¤ļ
    -0.07
    /display
    -0.07
    å¤ļå¾Ĺ
    -0.07
    oru
    -0.06
    &amp
    -0.06
    urt
    -0.06
    ä¹ĭ大
    -0.06
     maga
    -0.06
    POSITIVE LOGITS
    尼奥
    0.08
    æĶ¹éĿ©å¼ĢæĶ¾ä»¥æĿ¥
    0.08
    á»Ńa
    0.08
    è°ĵ
    0.07
     nafas
    0.07
    ì§ĵ
    0.07
    ccio
    0.07
    æĹłæĤĶ
    0.07
    ianya
    0.07
    utz
    0.07
    Activations Density 0.002%

    No Known Activations