© 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. 46399
    Prev
    Next
    INDEX
    Explanations

    triplet formation or loss

    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
    entino
    -0.08
    ernt
    -0.07
    æĶ¾çŁ¢
    -0.07
    enticate
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    ecer
    -0.07
    itin
    -0.07
    izo
    -0.07
    endir
    -0.07
    enticated
    -0.07
    POSITIVE LOGITS
     halinde
    0.10
    /array
    0.09
    /column
    0.09
    RARY
    0.08
    /octet
    0.07
    常åĬ¡å§Ķåijĺä¼ļ
    0.07
    /group
    0.07
    AZE
    0.07
    Ñĩики
    0.07
     {[
    0.07
    Activations Density 0.004%

    No Known Activations