© 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. 16180
    Prev
    Next
    INDEX
    Explanations

    Chinese place names and proper nouns

    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
    åİ®
    -0.07
     childs
    -0.07
    çľĭ好çļĦ
    -0.07
    [ii
    -0.06
     learnt
    -0.06
    â
    -0.06
    ç»
    -0.06
    é²²
    -0.06
    çĴĥ
    -0.06
    人ä½ĵçļĦ
    -0.06
    POSITIVE LOGITS
    uide
    0.07
    enam
    0.07
    paired
    0.07
    uwd
    0.07
    ï¸ı
    0.07
    arren
    0.07
    -multi
    0.06
    nah
    0.06
    æķ´æ²»å·¥ä½ľ
    0.06
    å·¡
    0.06
    Activations Density 0.051%

    No Known Activations