© 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. 62919
    Prev
    Next
    INDEX
    Explanations

    smallest value

    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
    amana
    -0.07
    æĪijåĴĮæĪijçļĦ
    -0.07
    alar
    -0.07
    éĤ£ä½į
    -0.07
    loor
    -0.07
    ække
    -0.07
    åħĪåĪ°åħĪå¾Ĺ
    -0.07
    çıłå®Ŀé¦ĸ饰
    -0.07
    è¿ĺåºĶå½ĵ
    -0.07
    Iterable
    -0.07
    POSITIVE LOGITS
    ieg
    0.07
    ä¹ĭçİĭ
    0.07
    inson
    0.07
    út
    0.07
    ض
    0.06
    ytt
    0.06
    ourd
    0.06
    åIJĪæ³ķçļĦ
    0.06
    à¸Ħà¸Ń
    0.06
     haft
    0.06
    Activations Density 0.001%

    No Known Activations