© 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. 39578
    Prev
    Next
    INDEX
    Explanations

    place names followed by punctuation

    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
    åĪĨå·¦åı³
    -0.07
    伪
    -0.07
    iloc
    -0.07
    åĢĴ
    -0.07
    æĴ
    -0.06
    eke
    -0.06
    رÙĥ
    -0.06
    æ°ijæĥħ
    -0.06
    luv
    -0.06
     either
    -0.06
    POSITIVE LOGITS
    trand
    0.08
    ä¸Ĭæĸ°
    0.07
    alice
    0.07
    bout
    0.07
    åľŁè±ª
    0.07
    à¹Ģสม
    0.07
    ãĤ¯ãĤ¿
    0.07
     Selatan
    0.07
    =*/
    0.07
    åĪ¤å¤ĦæľīæľŁå¾ĴåĪij
    0.06
    Activations Density 0.029%

    No Known Activations