© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 947
    Prev
    Next
    INDEX
    Explanations

    countries

    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
    ÑģÑı
    -0.10
     gì
    -0.09
    £
    -0.08
    eds
    -0.08
    ly
    -0.07
    ered
    -0.07
    δήÏĢοÏĦε
    -0.07
    ترÛĮÙĨ
    -0.07
    wers
    -0.07
    åľĪ
    -0.07
    POSITIVE LOGITS
    å¢ĥåĨħçļĦ
    0.10
    -China
    0.09
     Raya
    0.09
    opoly
    0.08
    -wide
    0.08
    áĬķ
    0.08
     entière
    0.08
    åĴĮä¸Ĭæµ·
    0.08
    ograd
    0.08
    's
    0.08
    Activations Density 0.355%

    No Known Activations