© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61874
    Prev
    Next
    INDEX
    Explanations

    chorus, epilogue, preface, introduction

    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
    lesh
    -0.09
    çŁ³æ¡¥
    -0.08
    å¸Ŀéĥ½
    -0.07
     Lets
    -0.07
    ijing
    -0.07
    糯米
    -0.07
    æ¼Ķ
    -0.07
    orent
    -0.07
    糯
    -0.07
    midt
    -0.07
    POSITIVE LOGITS
    æŶæĬ¥
    0.07
    veda
    0.06
    ä¼ij
    0.06
    å¦Ĥ对
    0.06
    Stub
    0.06
    è´¥
    0.06
    uais
    0.06
    tober
    0.06
     Bened
    0.06
     pose
    0.06
    Activations Density 0.001%

    No Known Activations