© 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. 1491
    Prev
    Next
    INDEX
    Explanations

    final conclusion

    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
    eldon
    -0.07
    alent
    -0.07
    ytu
    -0.07
    lime
    -0.07
    unto
    -0.07
     handy
    -0.06
    å¥ĩèīº
    -0.06
     yourselves
    -0.06
    åĩłå£°
    -0.06
    ä¸Ģ鸣
    -0.06
    POSITIVE LOGITS
    å½»åºķ
    0.08
    ç®ĢåĮĸ
    0.08
     finally
    0.08
     finalmente
    0.07
    çµĤæĸ¼
    0.07
    __:
    0.07
    åĨįåģļ
    0.07
    ç»Īäºİåı¯ä»¥
    0.07
    éĩįæĿ¥
    0.07
    缴åĪ°çİ°åľ¨
    0.07
    Activations Density 0.004%

    No Known Activations