© 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. 2590
    Prev
    Next
    INDEX
    Explanations

    eland, Gallium-Arsenide, balansen

    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
    Backing
    -0.07
    佳人
    -0.07
    åħīåįİ
    -0.07
    amp
    -0.07
    åµĺ
    -0.07
    มà¸Ļ
    -0.06
    ковÑģкого
    -0.06
    algo
    -0.06
    upas
    -0.06
    ODB
    -0.06
    POSITIVE LOGITS
    0.13
    èģĮä¸ļåѦéĻ¢
    0.08
    óta
    0.08
    ×Ļ×ķ×Ŀ
    0.07
    สà¹Į
    0.07
    ÂŃi
    0.07
    à¸ķà¹Į
    0.07
    Äħc
    0.07
    зиаÑĤ
    0.07
    ium
    0.07
    Activations Density 0.087%

    No Known Activations