© 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. 7608
    Prev
    Next
    INDEX
    Explanations

    ball projectile particle 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
    éļĶ
    -0.07
    éļĶæĸŃ
    -0.07
    ew
    -0.07
    entes
    -0.06
    ä¸ĬéŨ
    -0.06
    iller
    -0.06
    ipur
    -0.06
    ä¸ŃåįĹ
    -0.06
    å³»
    -0.06
    feeding
    -0.06
    POSITIVE LOGITS
     маÑģÑģой
    0.11
    è¿IJåĬ¨çļĦ
    0.09
     moving
    0.09
     mover
    0.09
    à¹Ģà¸Ħลืà¹Īà¸Ńà¸Ļ
    0.09
    çļĦè¿IJåĬ¨
    0.08
    çļĦ移åĬ¨
    0.08
     trajectory
    0.08
     movable
    0.08
    移åĬ¨çļĦ
    0.08
    Activations Density 0.160%

    No Known Activations