© 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. 23633
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ÑĮÑĪе
    -0.07
    aly
    -0.07
    linger
    -0.06
    stick
    -0.06
    èĮ¸
    -0.06
    buquerque
    -0.06
    å¥ł
    -0.06
    atty
    -0.06
    åįĹçľģ
    -0.06
    ä¹ĭåŁİ
    -0.06
    POSITIVE LOGITS
     halnya
    0.08
    azar
    0.08
     beis
    0.08
    翼翼
    0.08
    ean
    0.08
    大大å°ıå°ıçļĦ
    0.08
    俱ä¹IJéĥ¨
    0.07
    stvÃŃ
    0.07
    éģĵæĿ¥
    0.07
    ITERAL
    0.07
    Activations Density 0.059%

    No Known Activations