© 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. 13215
    Prev
    Next
    INDEX
    Explanations

    technology or services

    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
    ä¹ĭ以
    -0.08
    è·»
    -0.07
    åIJĪãģĦ
    -0.07
    æĬĢæľ¯çļĦåºĶçĶ¨
    -0.07
    å·¥ä½ľçļĦå¼Ģå±ķ
    -0.07
    ึà¸ĩ
    -0.06
    æ´»åĬ¨çļĦå¼Ģå±ķ
    -0.06
    agna
    -0.06
     occurring
    -0.06
    ubl
    -0.06
    POSITIVE LOGITS
    çļĦè¿ĩç¨ĭä¸Ń
    0.09
    ovich
    0.09
    æĪĸåľ¨
    0.08
    æ¯ĶåĪ«äºº
    0.08
     anonymously
    0.08
    åIJĪåIJĮæŶ
    0.08
    inic
    0.08
    å»
    0.08
    并æİ¥åıĹ
    0.08
    æľīæĦŁ
    0.08
    Activations Density 0.592%

    No Known Activations