© 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. 42951
    Prev
    Next
    INDEX
    Explanations

    ideal gas and interacting particles

    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
    貫
    -0.09
    ÃŃb
    -0.08
    Äħcz
    -0.08
    pad
    -0.08
    צר
    -0.08
    æĹ¥åĪ¶
    -0.08
    eful
    -0.08
    جات
    -0.08
    Cake
    -0.08
    osing
    -0.07
    POSITIVE LOGITS
     gas
    0.09
    æ°Ķä½ĵ
    0.08
     gases
    0.08
    æĺ¯ä¸Ģ群
    0.08
    gas
    0.07
    çļĦæ°Ķä½ĵ
    0.07
     undergoing
    0.07
     obey
    0.07
     Gas
    0.07
     interacting
    0.07
    Activations Density 0.005%

    No Known Activations