© 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. 2321
    Prev
    Next
    INDEX
    Explanations

    pair, twin, rest, same, remaining

    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
    好åķĬ
    -0.08
    èĺ
    -0.08
    енÑģи
    -0.07
    ê»ı
    -0.07
    å°±æĭ¿
    -0.07
    /profile
    -0.07
     stride
    -0.07
    ä¼´ä½ł
    -0.07
     ridden
    -0.06
    åħ¨èĥľ
    -0.06
    POSITIVE LOGITS
    roat
    0.07
    èµĦæºIJåħ±äº«
    0.07
    ankan
    0.07
    çļĦèĩªçĶ±
    0.07
    åı¯ä»¥èĩªçĶ±
    0.07
    ropy
    0.07
    sharing
    0.06
    æĺ¯ä¸Ģ对
    0.06
    äºĴæį¢
    0.06
     birbir
    0.06
    Activations Density 0.029%

    No Known Activations