© 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. 22965
    Prev
    Next
    INDEX
    Explanations

    ketones

    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
    odus
    -0.08
    çī¹åĭĴ
    -0.07
    èļĮ
    -0.07
     Beli
    -0.07
    港å¸Ĥ
    -0.06
    à¸Ĭาà¸ķิ
    -0.06
    odos
    -0.06
    ìn
    -0.06
    å¢Ļ
    -0.06
     harbor
    -0.06
    POSITIVE LOGITS
    ssia
    0.09
    iture
    0.08
    zia
    0.08
    éŨä¸ĭ
    0.08
    ALAR
    0.08
    slash
    0.08
    ehm
    0.08
    onis
    0.08
    人æ°ijèŃ¦å¯Ł
    0.08
    cident
    0.07
    Activations Density 0.044%

    No Known Activations