© 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. 23306
    Prev
    Next
    INDEX
    Explanations

    description or implementation details

    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
    æ¸ł
    -0.07
    egin
    -0.07
    åĬ²
    -0.07
    boh
    -0.06
    à¹Ĥà¸ģ
    -0.06
    å°Ķ
    -0.06
    æľīæīĢ
    -0.06
    ITHER
    -0.06
    ä¹Łåı¯ä»¥æĺ¯
    -0.06
    uct
    -0.06
    POSITIVE LOGITS
    äºİè¡Į
    0.07
    ç»ĵæŀĦ设计
    0.07
     algorithm
    0.07
    æķ´å¥Ĺ
    0.07
    ä¸ĥæĹ¥
    0.07
     debugging
    0.07
     bugs
    0.07
    etton
    0.07
    Implemented
    0.07
    ยม
    0.07
    Activations Density 0.001%

    No Known Activations