© 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. 41697
    Prev
    Next
    INDEX
    Explanations

    states of matter and phase transitions

    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
    èĥĮæĻ¯çļĦ
    -0.07
    å¹´åįİ
    -0.07
     reused
    -0.07
    fos
    -0.07
     affair
    -0.07
    åįİéĺ³
    -0.07
    èĥĮæĻ¯å¢Ļ
    -0.07
    ionales
    -0.07
    åİĭåĻ¨
    -0.06
    æ¯ıä½į
    -0.06
    POSITIVE LOGITS
    åĽºæĢģ
    0.10
    ä½İ温
    0.09
    液æĢģ
    0.09
    åıĹçĥŃ
    0.09
    åĽºä½ĵ
    0.09
    -solid
    0.09
     пеÑĢеÑħода
    0.09
     transition
    0.09
    液ä½ĵ
    0.09
     temperature
    0.09
    Activations Density 0.006%

    No Known Activations