© 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. 27353
    Prev
    Next
    INDEX
    Explanations

    itself, product, zoom

    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
    èľ¿
    -0.08
    豺
    -0.08
     nowrap
    -0.08
    atina
    -0.08
    amad
    -0.08
    æĪ¿åľ°
    -0.07
    å·¥ä¸ļ大åѦ
    -0.07
    èݹ
    -0.07
    RING
    -0.07
    æĸ°éĹ»èµĦ讯
    -0.07
    POSITIVE LOGITS
    æĢ»
    0.07
    arter
    0.07
    åĬ¨
    0.06
    éĢģ礼
    0.06
    landers
    0.06
     total
    0.06
    å°ijæŀĹ
    0.06
    æĬ
    0.06
     distributes
    0.06
    大æľī
    0.06
    Activations Density 0.003%

    No Known Activations