© 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. 31133
    Prev
    Next
    INDEX
    Explanations

    two people

    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
    aign
    -0.07
    缸åºĶçļĦ
    -0.07
    äºĶ级
    -0.07
    town
    -0.07
    äºĨä¸ĭ
    -0.07
     Thin
    -0.07
    alth
    -0.07
    åİ»åĵªåĦ¿
    -0.07
    缸åºĶ
    -0.07
    æĿİ家
    -0.07
    POSITIVE LOGITS
     pairs
    0.16
     pair
    0.16
    çļĦ两个
    0.14
    ä¸Ģ对
    0.14
    å½¼æѤ
    0.14
    ä¿©
    0.14
     two
    0.14
     cặp
    0.13
    çļĦ两
    0.13
    å½¼æѤçļĦ
    0.13
    Activations Density 0.075%

    No Known Activations