© 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. 33527
    Prev
    Next
    INDEX
    Explanations

    labels followed by colon

    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
    ecca
    -0.07
    åºĶå½ĵä¾Ŀçħ§
    -0.07
    ument
    -0.07
    ä¸ĢåIJij
    -0.07
    yw
    -0.07
    :\/\/
    -0.07
    æĶ
    -0.07
    ä¼ļåijĺåįķä½į
    -0.07
    wdx
    -0.06
    EDAD
    -0.06
    POSITIVE LOGITS
    åĬłè½½æĽ´å¤ļ
    0.07
    鸾
    0.07
    caret
    0.07
    ugat
    0.06
    ä¸¥æł¼çļĦ
    0.06
    angkat
    0.06
    å¼ĢæĶ¾çļĦ
    0.06
    è®Ń
    0.06
     reckon
    0.06
     Paulista
    0.06
    Activations Density 0.091%

    No Known Activations