© 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. 61438
    Prev
    Next
    INDEX
    Explanations

    simpler, easier, alternatively

    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
    æĪĸåħ¶
    -0.07
    urr
    -0.06
    пÑĢаво
    -0.06
    æľ¬éĥ¨
    -0.06
    åģĩ设
    -0.06
     dess
    -0.06
    æ¡IJ乡
    -0.06
    egel
    -0.06
    egah
    -0.06
     Andrews
    -0.06
    POSITIVE LOGITS
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.11
    ä¹Łåı¯çĽ´æİ¥
    0.11
     simpler
    0.10
     alternatively
    0.10
    ä¹Łåı¯ä»¥çĶ¨
    0.09
     easier
    0.09
    ä¹Łåı¯ä»¥ä½¿çĶ¨
    0.09
    æĽ´ç¬¦åIJĪ
    0.09
    åı¦ä¸Ģç§į
    0.08
    ä¹Łåı¯
    0.08
    Activations Density 0.047%

    No Known Activations