© 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. 47832
    Prev
    Next
    INDEX
    Explanations

    either/or

    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
    _RESERVED
    -0.08
    åĪĨå·¥
    -0.07
    á»ģn
    -0.07
    æľ¬æĸĩçĶ±
    -0.07
    sdale
    -0.07
    æĪĸåħ¶
    -0.07
     inters
    -0.07
    oon
    -0.07
    ä¸įåĮħæĭ¬
    -0.07
    à¹īาว
    -0.07
    POSITIVE LOGITS
    åIJĮæĹ¶ä¹Łåı¯ä»¥
    0.13
    åIJĮæŶåıĪ
    0.13
     both
    0.12
    åIJĮæĹ¶ä¹Łæĺ¯
    0.12
     simultaneously
    0.12
    æĹ¢æĺ¯
    0.12
     BOTH
    0.12
    åIJĮæŶ
    0.12
    ä½ĨåIJĮæŶ
    0.11
    åIJĮæĹ¶åľ¨
    0.11
    Activations Density 0.151%

    No Known Activations