© 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. 23189
    Prev
    Next
    INDEX
    Explanations

    know that or know to

    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
    igura
    -0.08
    uly
    -0.08
    ä½łæľī没æľī
    -0.08
     addirittura
    -0.08
    ä½łæĺ¯ä¸įæĺ¯
    -0.08
    æľīä½ķ
    -0.08
    æľī没æľī
    -0.07
    æľīä»Ģä¹ĪåĮºåĪ«
    -0.07
     appropriately
    -0.07
    æį¢åı¥è¯Ŀ说
    -0.07
    POSITIVE LOGITS
    already
    0.08
    说è¦ģ
    0.08
     already
    0.08
     giÃł
    0.08
    elah
    0.07
    å¼ı
    0.07
    æĪijä»¬çŁ¥éģĵ
    0.07
    缮æłĩæĺ¯
    0.07
    layui
    0.07
     déjÃł
    0.07
    Activations Density 0.026%

    No Known Activations