© 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. 50226
    Prev
    Next
    INDEX
    Explanations

    even, tampoco, nemmeno

    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
    身åıĹ
    -0.07
    个人æĪĸ
    -0.07
    istes
    -0.07
    onat
    -0.07
    æĺŁæµ·
    -0.07
    å¦ĸåŃ½
    -0.07
    åı«å¥½
    -0.07
    .abstract
    -0.07
    Works
    -0.07
    çľ¼çķĮ
    -0.07
    POSITIVE LOGITS
    ë§ĪìłĢ
    0.12
    ãģĻãĤī
    0.12
    ä¹Łæ²¡æľī
    0.11
     tampoco
    0.10
    æĪijä¹Łä¸į
    0.10
    ä¹Łä¸įèĥ½
    0.10
    ä¹Łä¸į
    0.10
     even
    0.10
    ä¹Łä¸įè¡Į
    0.10
     nemmeno
    0.10
    Activations Density 0.118%

    No Known Activations