© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62884
    Prev
    Next
    INDEX
    Explanations

    same words or punctuation

    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
    åħ¨æĸ°ä¸Ģ代
    -0.08
    бок
    -0.08
     instead
    -0.08
     invece
    -0.08
    èĢĮä¸įæĺ¯
    -0.07
    instead
    -0.07
    ķĮ
    -0.07
    è¿ľä½İäºİ
    -0.07
    æīįæĺ¯
    -0.07
    åĩºå¥ĩ
    -0.07
    POSITIVE LOGITS
    åIJĮæł·
    0.09
    åıªä¸įè¿ĩæĺ¯
    0.09
    ä¸įè¿ĩæĺ¯
    0.08
    åģļçļĦå°±æĺ¯
    0.08
    åıªä¸įè¿ĩ
    0.08
     similarly
    0.08
    åıªè¦ģèĥ½
    0.08
    ä¹Łä¸Ģæł·
    0.08
     same
    0.08
    åIJĮæł·æĺ¯
    0.08
    Activations Density 0.018%

    No Known Activations