© 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. 1343
    Prev
    Next
    INDEX
    Explanations

    Chinese names and scripts

    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
    <quote
    -0.09
    éģ®æİ©
    -0.07
    èĥ½å¤Łå°Ĩ
    -0.07
    ativer
    -0.07
    preuves
    -0.07
    麦å½ĵ
    -0.07
    à¹ģลà¸ģ
    -0.07
    éĢĢå½¹åĨĽäºº
    -0.07
     quotations
    -0.07
    ÏĨÏĮ
    -0.07
    POSITIVE LOGITS
    æĿ¥è¯´æĺ¯
    0.09
    ë¡ľëĬĶ
    0.08
    ìľ¼ë¡ľëĬĶ
    0.08
    çļĦè¯Ŀ
    0.07
    :
    0.07
    åĪĨåĪ«ä¸º
    0.07
    odium
    0.07
    ommer
    0.07
    éŃĦ
    0.07
    å¼ı为
    0.06
    Activations Density 0.074%

    No Known Activations