© 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. 23586
    Prev
    Next
    INDEX
    Explanations

    PA, UL, repository, trees, spokesperson

    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
    éºĴ
    -0.08
    缨
    -0.07
    æĹ¥çĶŁ
    -0.06
    丧
    -0.06
    yum
    -0.06
    ä¸įæ¸Ŀ
    -0.06
    éħĿ
    -0.06
    é»Ķ
    -0.06
    éĩĩ
    -0.06
    èŃ
    -0.06
    POSITIVE LOGITS
    éĴĪ对
    0.10
    ä»»ä½ķä¸Ģç§į
    0.09
    éĩĿå°į
    0.09
    åIJĦè¡Įä¸ļ
    0.09
    æŁIJä¸Ģ
    0.09
    ä»»ä½ķä¸ľè¥¿
    0.09
    æĺ¯éĴĪ对
    0.09
    åIJĦé¢ĨåŁŁ
    0.08
    IndexOf
    0.08
    éĴĪ对ä¸įåIJĮ
    0.08
    Activations Density 0.818%

    No Known Activations