© 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. 63306
    Prev
    Next
    INDEX
    Explanations

    outdoor spaces and yards

    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
    èĪªéģĵ
    -0.08
    ól
    -0.07
    çŁ¿äºķ
    -0.07
     Lod
    -0.07
     cavern
    -0.07
    lod
    -0.07
    åı¤åŁİ
    -0.07
    殿åłĤ
    -0.07
    车åİ¢
    -0.07
    å±±éĩĮ
    -0.07
    POSITIVE LOGITS
    å¼ĢéĺĶ
    0.11
    æĻĴ
    0.09
    à¸ģวà¹īาà¸ĩ
    0.09
     area
    0.09
    สาà¸ĺารà¸ĵะ
    0.09
     grounds
    0.09
    åĿª
    0.09
    éĿ¢ç§¯ä¸º
    0.08
    æļ´æĻĴ
    0.08
    èįīåĿª
    0.08
    Activations Density 0.218%

    No Known Activations