© 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. 42001
    Prev
    Next
    INDEX
    Explanations

    solar, equinox, solstice, annual, year, season

    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
    _noise
    -0.08
    å¾·åįİ
    -0.08
    æ±Łæµ·
    -0.08
    ç§ģä¸ĭ
    -0.08
    æ°´æµĴ
    -0.07
    éĩįéĩijå±ŀ
    -0.07
    Metal
    -0.07
    éĩijå±ŀ
    -0.07
    orado
    -0.07
     intox
    -0.07
    POSITIVE LOGITS
    缴å°Ħ
    0.12
    æĺ¯ä¸Ģå¹´
    0.10
     solar
    0.10
     annual
    0.10
    åĨ¬èĩ³
    0.09
     annually
    0.08
    æİĪ
    0.08
     ÑģолнÑĨе
    0.08
     yearly
    0.08
    太éĺ³
    0.08
    Activations Density 0.016%

    No Known Activations