© 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. 55466
    Prev
    Next
    INDEX
    Explanations

    with counterparts

    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
    两人çļĦ
    -0.09
    åħļåijĺçļĦ
    -0.08
    两个人çļĦ
    -0.08
    å¾·éŁ³
    -0.08
    女åŃIJçļĦ
    -0.08
    人人éĥ½
    -0.08
    ä¸ŃåĽ½åľ¨
    -0.08
    ä¼ģä¸ļåıĹçĽĬ
    -0.08
    resent
    -0.08
    å°ı妹
    -0.08
    POSITIVE LOGITS
     counterparts
    0.09
     counterpart
    0.09
    çļĦ对象
    0.09
     other
    0.08
    åĴĮæĢĿèĢĥ
    0.08
     gỡ
    0.08
     fellow
    0.08
     peers
    0.08
    èĩªå·±çļĦ缮æłĩ
    0.07
    å¿ĥ仪
    0.07
    Activations Density 0.477%

    No Known Activations