© 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. 57138
    Prev
    Next
    INDEX
    Explanations

    percentage of

    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
    诸å¤ļ
    -0.09
    หลาย
    -0.08
     многим
    -0.08
     several
    -0.07
    หลายà¹Ĩ
    -0.07
     многиÑħ
    -0.07
    好åĩł
    -0.07
    audi
    -0.07
    æīĢæľī
    -0.07
    èĢĢ
    -0.07
    POSITIVE LOGITS
    ä¸įåIJĮç¨ĭ度
    0.10
    ä¸įåIJĮç¨ĭ度çļĦ
    0.10
     ëĦĺëĬĶ
    0.08
    缴æİ¥æĪĸéĹ´æİ¥
    0.08
     antaranya
    0.08
    ìĶ©
    0.08
    è°ĵä¹ĭ
    0.08
     effettivamente
    0.07
     altrett
    0.07
    缴æİ¥æĪĸ
    0.07
    Activations Density 0.285%

    No Known Activations