© 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. 48247
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
    ool
    -0.07
    ik
    -0.07
    azel
    -0.07
    anga
    -0.06
    ide
    -0.06
    orda
    -0.06
    姬
    -0.06
    chie
    -0.06
    åĬŀæ³ķ
    -0.06
    ׼×ķ
    -0.06
    POSITIVE LOGITS
    äten
    0.09
    åħ±ç®¡
    0.08
    硬çļĦ
    0.08
    tease
    0.07
    SSIP
    0.07
    é¢ĿçļĦ
    0.07
    åĩºçº¿
    0.07
    tés
    0.07
    åį«ä¸ľ
    0.07
    деÑĢ
    0.07
    Activations Density 0.038%

    No Known Activations