© 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. 28505
    Prev
    Next
    INDEX
    Explanations

    up, rate, vertical, lift, drive

    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¸Ĭè¡Ĺ
    -0.08
    æĿ¾
    -0.08
    åħ¨é¢Ŀ
    -0.07
    åħ¨çĽĺ
    -0.07
    beam
    -0.07
    çļ¿
    -0.07
    Ĵ
    -0.07
    oad
    -0.07
    åľĪ
    -0.07
    满åłĤ
    -0.07
    POSITIVE LOGITS
    åĬ¨èĥ½
    0.10
    ä¸įæĢ¥
    0.08
    VEL
    0.08
    pace
    0.07
     momentum
    0.07
     slowed
    0.07
    åĭ¢
    0.07
    å·´åĭĴ
    0.07
    ä¸įåIJ¬
    0.07
     movement
    0.07
    Activations Density 0.001%

    No Known Activations