© 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. 11635
    Prev
    Next
    INDEX
    Explanations

    application where needed

    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
    ä½įåľ¨
    -0.09
    çķĻåľ¨
    -0.08
    ãģĵãĤĮãģ§
    -0.08
    rix
    -0.08
    åĺĽ
    -0.07
    好åIJĹ
    -0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.07
    åģľåľ¨
    -0.06
     hereby
    -0.06
    åľ¨éĢĻ
    -0.06
    POSITIVE LOGITS
    说äºĨç®Ĺ
    0.08
    æľĢ为
    0.08
    æľĢæľī
    0.08
     инÑĭм
    0.08
    ç±ģ
    0.08
     ÙĪÙĬÙĥÙĪÙĨ
    0.08
    ä½ķåľ°
    0.08
    à¸ŀà¸Ńà¸Ķี
    0.08
    veis
    0.07
    åıĪåĪ°
    0.07
    Activations Density 0.220%

    No Known Activations