© 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. 8048
    Prev
    Next
    INDEX
    Explanations

    physical states or properties

    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
    幸
    -0.08
    usch
    -0.08
    CVE
    -0.07
    æ¯ħ
    -0.07
    æĺ¯ä¸Ģ段
    -0.07
    åĽłä¸ºæĺ¯
    -0.07
    REET
    -0.07
    à¸ģà¹ĩà¸ķาม
    -0.07
    åĽłåħ¶
    -0.07
    ׼×Ļ
    -0.07
    POSITIVE LOGITS
    ä»İèĢĮ
    0.10
    ä»İèĢĮ使
    0.09
     thereby
    0.09
    è¿ĽèĢĮ
    0.08
    ãģ¨ãģªãĤĬ
    0.08
    å¾ŀèĢĮ
    0.08
     _______,
    0.08
    ä»İèĢĮ导èĩ´
    0.08
    äºİæĺ¯åľ¨
    0.07
     consequently
    0.07
    Activations Density 0.102%

    No Known Activations