© 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. 50502
    Prev
    Next
    INDEX
    Explanations

    significant point

    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
    åĪĨå¸ĥåľ¨
    -0.07
     constantly
    -0.07
    ä¸įä¸Ģä¼ļåĦ¿
    -0.07
    æ¶Ī磨
    -0.07
    ä¸Ģ大åłĨ
    -0.07
    éļıå¤Ħ
    -0.07
    -bs
    -0.07
    æºIJæºIJ
    -0.06
    ä¹ħèĢĮä¹ħä¹ĭ
    -0.06
    ä¸įåİĮ
    -0.06
    POSITIVE LOGITS
    åĪĨæ°´
    0.12
    æĦıä¹īéĩį大
    0.12
    éĩĮç¨ĭç¢ij
    0.11
    æłĩå¿ĹçĿĢ
    0.11
    çļĦå¼Ģå§ĭ
    0.11
    转æĬĺçĤ¹
    0.11
    è¿ĪåIJij
    0.10
    å¼ĢåIJ¯
    0.10
    è¿Īåħ¥
    0.10
     озна
    0.10
    Activations Density 0.246%

    No Known Activations