© 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. 26159
    Prev
    Next
    INDEX
    Explanations

    moving around

    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
    åĢĶ强
    -0.07
    éĤ£ä¸ĢåĪ»
    -0.07
     squarely
    -0.07
    缴æİ¥
    -0.07
    chie
    -0.07
    itev
    -0.06
    è¿Īåĩº
    -0.06
     handshake
    -0.06
    sis
    -0.06
    缴éĿ¢
    -0.06
    POSITIVE LOGITS
     khắp
    0.13
    éģį
    0.12
    寻æī¾
    0.12
    游走
    0.12
    å·¡è§Ĩ
    0.12
    éģįäºĨ
    0.12
    ç©¿æ¢Ń
    0.12
    漫游
    0.11
     freely
    0.11
    å·¡åĽŀ
    0.11
    Activations Density 0.227%

    No Known Activations