© 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. 57088
    Prev
    Next
    INDEX
    Explanations

    else block structure

    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
    ÙħÙĬ
    -0.08
    ä¸Ģæĸij
    -0.07
    太éĥİ
    -0.07
    ÏĢε
    -0.07
    ì§ĵ
    -0.07
    _FALSE
    -0.07
    rus
    -0.07
    ableView
    -0.07
    åŃĹåŀĭ
    -0.07
    zada
    -0.07
    POSITIVE LOGITS
    æŃ£å¸¸
    0.08
    âľħ
    0.08
    åĪĻåı¯ä»¥
    0.08
    æīįè¡Į
    0.08
    åĪĻåı¯
    0.08
     normal
    0.08
    æŃ£å¸¸ä½¿çĶ¨
    0.08
     dagegen
    0.07
    åĪļåĪļ好
    0.07
    ä¼ĺè´¨çļĦ
    0.07
    Activations Density 0.160%

    No Known Activations