© 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. 3291
    Prev
    Next
    INDEX
    Explanations

    rate or extent of change

    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
    å°½äºĨ
    -0.09
    缴æİ¥çĶ¨
    -0.09
    ä»Ķç»Ĩéĺħ读
    -0.08
    ä»Ķç»Ĩçľĭ
    -0.08
    缸äºĴéħįåIJĪ
    -0.08
    strup
    -0.08
    è¿Ľä¸ĢæŃ¥æıIJé«ĺ
    -0.08
    ä¸įæĸŃæݢ索
    -0.08
    å¾Īæ¸ħæ¥ļ
    -0.08
     ë°ĺëĵľìĭľ
    -0.08
    POSITIVE LOGITS
    íŀĪ
    0.08
    åľ°ä»İ
    0.08
    åľ°åIJij
    0.08
    ly
    0.07
    åľ°å°Ĩ
    0.07
    èĢĮæĿ¥
    0.07
    aneously
    0.07
    ely
    0.06
    èĢĮèĩ³
    0.06
    ä½ľåĵį
    0.06
    Activations Density 0.003%

    No Known Activations