© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    $\int$ and $\Omega$

    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
     Bender
    -0.07
    æ¡Ķ
    -0.06
    adesh
    -0.06
    åħ¶è§ĤçĤ¹
    -0.06
    æľºåĪ¶
    -0.06
    ãģĭãģķ
    -0.06
    ä¹ĿéľĦ
    -0.06
    kia
    -0.06
    åľ¨é©¬
    -0.06
     Maj
    -0.06
    POSITIVE LOGITS
    åı¯ä»¥æĺ¯
    0.08
    èĭ¥éĿŀ
    0.08
    æıĴ
    0.07
    æĬĺ
    0.07
    ìĬ¨
    0.07
    åı¯ä¸º
    0.07
     possibil
    0.07
    åħ¬å¼ı
    0.07
    æľĢä¸ĵä¸ļçļĦ
    0.07
    Formula
    0.07
    Activations Density 0.038%

    No Known Activations