© 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. 22388
    Prev
    Next
    INDEX
    Explanations

    electric motor and operation

    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
    èĦĨå¼±
    -0.09
    .nano
    -0.08
    itty
    -0.08
    èĦĨå¼±çļĦ
    -0.07
    Nano
    -0.07
    åģľçīĮ
    -0.07
     nano
    -0.07
     Libraries
    -0.07
    纤
    -0.07
    йд
    -0.07
    POSITIVE LOGITS
    è½¬çŁ©
    0.09
     torque
    0.09
    çĶµåĬ¨æľº
    0.08
    ynos
    0.08
    çĶ©
    0.07
    åĬ±
    0.07
     induction
    0.07
    å®ļåŃIJ
    0.07
     vocational
    0.07
    转åŃIJ
    0.07
    Activations Density 0.008%

    No Known Activations