© 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. 19173
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by conjunctions or numbers

    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
    åĴĮèĶ¬èıľ
    -0.08
    åĴĮçĶ°
    -0.07
    ensions
    -0.07
     manier
    -0.07
    ither
    -0.07
     mercoledì
    -0.06
    èĨ³
    -0.06
    æĮĸæİĺåħ¬åı¸
    -0.06
    ä¹ĭé¤ĺ
    -0.06
    åįĹåĮº
    -0.06
    POSITIVE LOGITS
    以ä¸Ĭ
    0.07
    exual
    0.07
    ä¸įè¨Ģ
    0.07
    èĮ«èĮ«
    0.07
    å°ıç»ĵ
    0.07
    人以ä¸Ĭ
    0.07
    åIJĮå¿ĥ
    0.07
    acin
    0.07
    _finalize
    0.06
    è¿ĻäºĽè¯Ŀ
    0.06
    Activations Density 0.035%

    No Known Activations