© 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. 14054
    Prev
    Next
    INDEX
    Explanations

    globally, century, year

    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
    æĪĸåħ¶å®ĥ
    -0.09
     perchè
    -0.09
    ä¸İåħ¶å®ĥ
    -0.09
    åģļ为
    -0.09
     favour
    -0.08
    åĴĮåħ¶å®ĥ
    -0.08
     succesfully
    -0.08
     seperate
    -0.08
     recognise
    -0.08
     ÙģÙī
    -0.08
    POSITIVE LOGITS
    0.14
    0.09
    ãģķãģ¾ãģĸãģ¾ãģª
    0.08
    rea
    0.08
    ÙĬرÙĭا
    0.08
    å©Ģ
    0.08
    usted
    0.08
    __.__
    0.08
    iché
    0.08
    LETE
    0.08
    Activations Density 0.613%

    No Known Activations