© 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. 43597
    Prev
    Next
    INDEX
    Explanations

    Council invited

    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
    éĢļåĪĻ
    -0.09
    èĦ±
    -0.08
    ãģķãģĦ
    -0.08
    love
    -0.08
    æĪ·æĻĵ
    -0.07
     bÃło
    -0.07
     '.',
    -0.07
     Visu
    -0.07
    prise
    -0.07
    波纹管
    -0.07
    POSITIVE LOGITS
    ÄĽr
    0.07
    å°±è¶Ĭ
    0.07
    å°±ä¸įèĥ½
    0.06
    å°±æĺ¾å¾Ĺ
    0.06
     becomes
    0.06
    æĺ¾å¾Ĺæł¼å¤ĸ
    0.06
    åĴĮæĵįä½ľ
    0.06
    å°Ĩè¿İæĿ¥
    0.06
    å°±ä¸įåĨį
    0.06
    åŁİåĮĹ
    0.06
    Activations Density 0.181%

    No Known Activations