© 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. 18835
    Prev
    Next
    INDEX
    Explanations

    resulting in

    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
     bowiem
    -0.07
    elik
    -0.07
    åĽłä¸º
    -0.07
     meanwhile
    -0.07
    åĽłä¸ºæľī
    -0.07
    åĽłä¸ºä½ł
    -0.06
     totiž
    -0.06
    åĽłä¸ºæĺ¯
    -0.06
     because
    -0.06
     azért
    -0.06
    POSITIVE LOGITS
    rolet
    0.08
    alet
    0.08
    åĽŃè·¯
    0.08
     بدÙĪرÙĩ
    0.08
    æĪijåıªèĥ½
    0.08
    ا
    0.07
    é¦Ī
    0.07
    ÙĦا
    0.07
    æł¼å¤ĸçļĦ
    0.07
    ly
    0.07
    Activations Density 0.035%

    No Known Activations