© 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. 11905
    Prev
    Next
    INDEX
    Explanations

    maximum capacity

    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
    riot
    -0.08
     dér
    -0.07
    å¿łå®ŀ
    -0.07
    漪
    -0.07
    anza
    -0.07
    å·¥ä½ľçļĦåIJĮæŶ
    -0.07
    ë¡Ģ
    -0.07
    è²¼
    -0.07
    æľīè¯Ŀ
    -0.07
    stab
    -0.07
    POSITIVE LOGITS
     reached
    0.09
    大åħ³
    0.08
    Reached
    0.08
     Peker
    0.08
     rush
    0.08
    æŀģéĻIJ
    0.07
     limitless
    0.07
    æĭīåħĭ
    0.07
     capacity
    0.07
     unreachable
    0.07
    Activations Density 0.018%

    No Known Activations