© 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. 61724
    Prev
    Next
    INDEX
    Explanations

    overall 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
    缸åºĶ
    -0.07
    ä¼Ļ
    -0.07
    ç¾ŀ
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    çľĭä¸įè§ģ
    -0.07
    æĪĸæľª
    -0.06
    缸åºĶçļĦ
    -0.06
    æĹłå½±
    -0.06
    ihu
    -0.06
    æľīå¾ħ
    -0.06
    POSITIVE LOGITS
    ãģ¾ãģ¨ãĤģ
    0.10
    æĢ»ä¹ĭ
    0.09
     overall
    0.09
    éĢļè¿ĩ以ä¸Ĭ
    0.09
    èĩ³æѤ
    0.09
     insgesamt
    0.09
    综ä¸Ĭ
    0.09
    overall
    0.08
    æķ´ä½ĵ
    0.08
    çļĦ综åIJĪ
    0.08
    Activations Density 0.015%

    No Known Activations