© 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. 15183
    Prev
    Next
    INDEX
    Explanations

    code and math symbols

    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
    زÙĦ
    -0.07
    æįī
    -0.07
    ç»Ń
    -0.07
    æ´»çļĦ
    -0.07
    çļĦæŶåĪ»
    -0.07
    åľ¨ä»Ĭ
    -0.07
    æĹłåı¯
    -0.07
    ONY
    -0.07
    OSC
    -0.07
    à¥ĭà¤ľ
    -0.07
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯è¯´
    0.08
    æīĢ以
    0.08
    Ł
    0.07
     Yani
    0.07
     VáºŃy
    0.07
    upati
    0.07
    åĽłæѤ
    0.07
    isas
    0.07
    æĺ¯è¯¥
    0.07
    大å®ī
    0.07
    Activations Density 0.003%

    No Known Activations