© 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. 43608
    Prev
    Next
    INDEX
    Explanations

    velocity, speed, flow

    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
    æ¯Ķä¾ĭçļĦ
    -0.07
    åıªå¾Ĺ
    -0.06
    æķ°éĩıçļĦ
    -0.06
    è§Ħæł¼
    -0.06
    _RATIO
    -0.06
    次第
    -0.06
    æĿ¥è¿ĩ
    -0.06
    æ¯Ķä¾ĭ
    -0.06
     Ratio
    -0.06
    antha
    -0.06
    POSITIVE LOGITS
    odiac
    0.10
     velocity
    0.10
    velocity
    0.10
    è¿IJåĬ¨çļĦ
    0.09
     motions
    0.09
    è¿IJåĬ¨åĴĮ
    0.09
     velocities
    0.09
     kin
    0.09
    Velocity
    0.09
    彩äºij
    0.09
    Activations Density 0.007%

    No Known Activations