© 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. 18938
    Prev
    Next
    INDEX
    Explanations

    particle collisions

    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
    arters
    -0.08
    èĭ¦è¾£
    -0.08
    juh
    -0.08
    dataProvider
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    å¦Ĥä¸įæľį
    -0.08
    ç¡·
    -0.07
    麻麻
    -0.07
    DataContext
    -0.07
    éħ¸ç¢±
    -0.07
    POSITIVE LOGITS
    缸äºĴ
    0.08
    åįł
    0.08
    å½¼æѤ
    0.08
    身æĿIJ
    0.08
     interaction
    0.07
    interaction
    0.07
     mutual
    0.07
     collisions
    0.07
     occupancy
    0.07
     interactions
    0.06
    Activations Density 0.004%

    No Known Activations