© 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. 9111
    Prev
    Next
    INDEX
    Explanations

    metal ions with positive charge

    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
    eneg
    -0.08
    اتÙĩ
    -0.08
    atnya
    -0.08
    ÙĬÙĨ
    -0.08
    illons
    -0.08
    اتÙĩا
    -0.07
    ENTAL
    -0.07
    شارات
    -0.07
    ormal
    -0.07
    اتÛĮ
    -0.07
    POSITIVE LOGITS
    0.11
    0.10
    ï¸ı
    0.10
    0.09
    äºĭåįĬåĬŁåĢį
    0.08
    夫æĸ¯åŁº
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    åĭĩå¾Ģ缴åīį
    0.07
    �
    0.07
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    Activations Density 0.014%

    No Known Activations