© 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. 65429
    Prev
    Next
    INDEX
    Explanations

    cultural concepts and progress

    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
    áĢ®áĢ¸
    -0.08
    çİĩåĴĮ
    -0.07
    åıĬ缸åħ³
    -0.07
    åĴĮæĶ¯æĮģ
    -0.07
    åıĪ称
    -0.07
    éri
    -0.07
    à¹ģละà¸Ħวาม
    -0.07
    æĶ¯æĮģä¸İ
    -0.07
    åı·åĴĮ
    -0.06
    å¸Ĥä¸Ń
    -0.06
    POSITIVE LOGITS
    ä¸įæĭĶ
    0.08
    ãģ¨ãģĦãģ£ãģŁ
    0.08
    缸ç»ĵåIJĪ
    0.08
    áŁĭ
    0.07
    /etc
    0.07
    iks
    0.07
    whatever
    0.07
     ÙĪØŃتÙī
    0.07
    缸ç»ĵåIJĪçļĦ
    0.07
    .gz
    0.07
    Activations Density 0.011%

    No Known Activations