© 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. 26924
    Prev
    Next
    INDEX
    Explanations

    Chinese place names and romanizations

    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
    åĪĩãĤĬ
    -0.07
    ÑijÑĢ
    -0.07
    dal
    -0.07
    inga
    -0.06
     ÙĩÙħ
    -0.06
    ÙĨا
    -0.06
    عب
    -0.06
    Queries
    -0.06
    Âł
    -0.06
     Tanner
    -0.06
    POSITIVE LOGITS
    obao
    0.09
    hei
    0.09
    Ñģполни
    0.08
    ï´
    0.08
    /XMLSchema
    0.08
    ufen
    0.08
    à¥ĩष
    0.08
    顺é£İ
    0.08
     autonome
    0.08
    acute
    0.07
    Activations Density 0.115%

    No Known Activations