© 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. 10319
    Prev
    Next
    INDEX
    Explanations

    flight and projectile movement

    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
     Sauna
    -0.08
    çĤ¼åĮĸ
    -0.08
     iceberg
    -0.07
    ç°ĩ
    -0.07
    大åĪ°
    -0.07
     পরি
    -0.07
    awei
    -0.07
     churn
    -0.07
    heimer
    -0.07
    heim
    -0.07
    POSITIVE LOGITS
    åľ¨ç©ºä¸Ń
    0.10
    æĬĽçī©
    0.09
     Projectile
    0.09
     projectile
    0.08
     landing
    0.08
    Projectile
    0.08
    æľĢéķ¿
    0.08
    èIJ½åľ°
    0.07
    空ä¸Ń
    0.07
     Horizontal
    0.07
    Activations Density 0.006%

    No Known Activations