© 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. 47271
    Prev
    Next
    INDEX
    Explanations

    movement and location

    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
    aker
    -0.08
    æºIJèĩª
    -0.07
     sourced
    -0.07
    跳水
    -0.07
    æīijéĿ¢èĢĮæĿ¥
    -0.07
    åŀ®
    -0.06
     dipping
    -0.06
    uruh
    -0.06
     Sleeve
    -0.06
    _payments
    -0.06
    POSITIVE LOGITS
    å½ĵåīįä½įç½®
    0.12
    移åĬ¨
    0.11
    移åĬ¨åĪ°
    0.11
    çļĦä½įç½®
    0.10
    çļĦ移åĬ¨
    0.10
    移åĭķ
    0.10
     movement
    0.10
     moveTo
    0.09
     moves
    0.09
    ä½įç½®
    0.09
    Activations Density 0.027%

    No Known Activations