© 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. 9412
    Prev
    Next
    INDEX
    Explanations

    structure factor statistical mechanics

    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
    çĶ¨æĪ·ä½¿çĶ¨
    -0.08
     airst
    -0.07
    athlete
    -0.07
    该éĻ¢
    -0.07
    reis
    -0.07
    powered
    -0.07
     payloads
    -0.07
     relais
    -0.07
    é£İåįİ
    -0.06
     Combined
    -0.06
    POSITIVE LOGITS
     density
    0.10
    ç»Łè®¡
    0.10
    density
    0.10
    å¯Ĩ度
    0.10
     statistical
    0.10
     Density
    0.09
     densities
    0.09
     statist
    0.09
     spatial
    0.09
     statistically
    0.09
    Activations Density 0.029%

    No Known Activations