© 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. 57893
    Prev
    Next
    INDEX
    Explanations

    going out

    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
    客æłĪ
    -0.08
    imon
    -0.08
     Shipping
    -0.07
     ìŬíĸīìŀIJ
    -0.07
    à¹Ģà¸Ĥà¹īาà¸ŀัà¸ģ
    -0.07
    icont
    -0.06
    æ¯ı天æĻļä¸Ĭ
    -0.06
     sbar
    -0.06
    åľ¨ä¸ĢæĹģ
    -0.06
    è¿Ľé©»
    -0.06
    POSITIVE LOGITS
     outing
    0.11
     outings
    0.09
    åĨĻçĶŁ
    0.08
    ä¸Ģè¶Ł
    0.08
    æł¡å¤ĸ
    0.08
    çļĦè·¯ä¸Ĭ
    0.08
    人å¤ļ
    0.08
    éĩĮåİ»
    0.08
    å®ŀ践活åĬ¨
    0.08
    åİ»çľĭ
    0.08
    Activations Density 0.413%

    No Known Activations