© 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. 3515
    Prev
    Next
    INDEX
    Explanations

    may, can, or could

    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
     Certain
    -0.07
    ernel
    -0.07
    åĽłä¸ºåľ¨
    -0.07
    æĽ´åħ¨
    -0.07
    åĨį说
    -0.07
    ä»Ĺ
    -0.07
    ä¸įèĥ½åĨį
    -0.06
     vẹn
    -0.06
    rica
    -0.06
    zam
    -0.06
    POSITIVE LOGITS
    ä¹Łåı¯ä»¥æĺ¯
    0.15
    æĹ¢åı¯ä»¥
    0.14
    åı¯ä»¥æĺ¯
    0.14
     either
    0.14
    å¤ļç§įå½¢å¼ı
    0.13
    æĹłè®ºæĺ¯
    0.12
    either
    0.12
     είÏĦε
    0.12
     entweder
    0.11
    çŃīå¤ļç§į
    0.11
    Activations Density 0.715%

    No Known Activations