© 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. 34692
    Prev
    Next
    INDEX
    Explanations

    relative velocity feedback or control

    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
    undles
    -0.08
    arp
    -0.07
    tores
    -0.07
    å°½
    -0.07
     dita
    -0.07
    tei
    -0.07
    æݧèĤ¡æľīéĻIJåħ¬åı¸
    -0.07
    åĴĮ建设
    -0.07
     piè
    -0.07
     mont
    -0.07
    POSITIVE LOGITS
    ovel
    0.08
    éĢŁåº¦
    0.08
     velocity
    0.08
    æľ¬äºº
    0.07
     currentState
    0.07
     впеÑĢед
    0.07
    磨
    0.07
    velocity
    0.07
    éĢŁåº¦åĴĮ
    0.07
    æij©æĵ¦
    0.07
    Activations Density 0.008%

    No Known Activations