© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37584
    Prev
    Next
    INDEX
    Explanations

    motor control systems

    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
    Negative Logits
    çŃĽæŁ¥
    -0.08
     AMD
    -0.07
     замеÑģÑĤи
    -0.07
    ixon
    -0.07
    ëŀĢ
    -0.07
    anced
    -0.06
    AMD
    -0.06
    _STACK
    -0.06
    uality
    -0.06
    Constructor
    -0.06
    POSITIVE LOGITS
     controlled
    0.08
     autonom
    0.08
     responds
    0.08
     иÑģполниÑĤелÑĮ
    0.08
     destinat
    0.08
    åĬ¨åĬĽç³»ç»Ł
    0.08
     indirectly
    0.08
    insky
    0.08
    æī§è¡Į
    0.07
    åħµé©¬
    0.07
    Activations Density 0.424%

    No Known Activations