© 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. 46316
    Prev
    Next
    INDEX
    Explanations

    UK, Controller, A, B, true/false

    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
    è¿Ļä¸ī
    -0.17
     trio
    -0.17
    è¿Ļä¸ī个
    -0.17
    è¿Ļä¸īç§į
    -0.17
    çļĦä¸ī个
    -0.16
    ä¸ī项
    -0.16
    ä¸īèĢħ
    -0.16
     ketiga
    -0.15
    ä¸ī人
    -0.15
    ä¸ī个
    -0.15
    POSITIVE LOGITS
    tra
    0.08
    两ä¸ĩ
    0.07
    unted
    0.07
    oras
    0.06
    iste
    0.06
    åıĮèī²
    0.06
    itte
    0.06
    acons
    0.06
    åıĮéĿ¢
    0.06
     Hill
    0.06
    Activations Density 0.094%

    No Known Activations