© 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. 20837
    Prev
    Next
    INDEX
    Explanations

    time and computer

    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
    enne
    -0.08
    ophilia
    -0.07
    åħįè´¹åıijå¸ĥ
    -0.07
    à¥įड
    -0.07
    пÑĢоÑĩем
    -0.07
    iskon
    -0.07
     ìķĦëĭĮê°Ģ
    -0.07
    æ¹ĥ
    -0.07
    REQ
    -0.07
    é¦Ļå±±
    -0.07
    POSITIVE LOGITS
    è¿Ļå°±æĺ¯
    0.08
     thereby
    0.08
    ä»İèĢĮ
    0.08
    utton
    0.08
    è¿Ļåı«
    0.08
    è¿Ļåľ¨
    0.07
    ä»İèĢĮè¾¾åĪ°
    0.07
     without
    0.07
    ä»İèĢĮ导èĩ´
    0.07
    æĿ¯éħĴ
    0.07
    Activations Density 0.134%

    No Known Activations