© 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. 14903
    Prev
    Next
    INDEX
    Explanations

    affiliate programs, licenses, source code, PLC

    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
    ãĢģ
    -0.08
    éįµ
    -0.07
    æĬĺ
    -0.07
    å½
    -0.07
    缸
    -0.07
    éĢł
    -0.07
    ocom
    -0.06
    ju
    -0.06
    rink
    -0.06
    öre
    -0.06
    POSITIVE LOGITS
    æĮĸæİĺåħ¬åı¸
    0.09
    åĴĮ幸ç¦ı
    0.07
    icles
    0.07
    çİĭæĸĩ
    0.07
    çļĦè¿Ļç§į
    0.07
    çļĦè¿ĻäºĽ
    0.07
    clid
    0.07
    æľī以ä¸ĭ
    0.07
    鼷æĸ¯
    0.07
    æľīèĩªå·±çļĦ
    0.07
    Activations Density 0.122%

    No Known Activations