© 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. 63147
    Prev
    Next
    INDEX
    Explanations

    endings of words

    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
    ié
    -0.07
     Cornell
    -0.07
    i
    -0.07
    屿
    -0.06
     Hib
    -0.06
    ier
    -0.06
     Hein
    -0.06
    æĿľçĶ«
    -0.06
     Lüb
    -0.06
    éļľç¢į
    -0.06
    POSITIVE LOGITS
    éĦĤå°Ķå¤ļ
    0.10
    æĻī
    0.10
    éĦĤå°Ķå¤ļæĸ¯
    0.10
    åij¼åĴĮ
    0.09
    POP
    0.09
    .Android
    0.09
    æĻĭ
    0.09
     Banjarmasin
    0.09
    æ½
    0.09
     Birmingham
    0.09
    Activations Density 0.827%

    No Known Activations