© 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. 57644
    Prev
    Next
    INDEX
    Explanations

    documentation sections

    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
    <|box_end|>
    -0.10
    åı°ä¸ĬçļĦ
    -0.07
    ingo
    -0.07
    inser
    -0.07
    istou
    -0.07
    ingly
    -0.07
    åIJij导
    -0.07
    æĿ¥ä¹ĭ
    -0.07
    åĨįæİ¥
    -0.07
    andon
    -0.07
    POSITIVE LOGITS
     examples
    0.07
    burg
    0.07
    æĴ°ç¨¿
    0.07
    examples
    0.07
    åŁ¹æ¤į
    0.07
    èѬ
    0.06
    вÑı
    0.06
    ãģµãĤĭ
    0.06
    flix
    0.06
    ä¾ĭåŃIJ
    0.06
    Activations Density 0.009%

    No Known Activations