© 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. 49175
    Prev
    Next
    INDEX
    Explanations

    velocity and speed calculations

    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
    ä¸ĭä¸Ģ代
    -0.08
     Alegre
    -0.08
    ä¸ŃéĿĴå¹´
    -0.08
    acan
    -0.07
    icales
    -0.07
    马è¹Ħ
    -0.07
    leven
    -0.07
    ê¸°ê³ł
    -0.07
     chim
    -0.07
     cascade
    -0.07
    POSITIVE LOGITS
    åľ¨è¿Ļ段æŶéĹ´
    0.11
     quãng
    0.08
     odom
    0.08
    è¿Ļ段æŶéĹ´
    0.08
    ä½į移
    0.08
    éģĭåĭķ
    0.08
    ç¢Į
    0.08
    è¿IJåĬ¨
    0.08
    çĶ¨æŶ
    0.07
     retr
    0.07
    Activations Density 0.003%

    No Known Activations