© 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. 58620
    Prev
    Next
    INDEX
    Explanations

    rights and responsibilities

    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
    UIL
    -0.09
    adesh
    -0.08
    çļĦä¸ĢåĪĩéĥ½
    -0.08
    충
    -0.08
    yli
    -0.08
    ç½¹æĤ£
    -0.08
    åį³ä½į
    -0.08
    ä¸įçŁ¥éģĵèĩªå·±
    -0.08
    uds
    -0.07
    tvr
    -0.07
    POSITIVE LOGITS
     whoever
    0.11
     whichever
    0.07
     Whoever
    0.07
     discretion
    0.07
    ä½ķæĸ¹
    0.07
    æĮĩå®ļçļĦ
    0.06
     respective
    0.06
     either
    0.06
    ä¸įåIJĮçļĦ人
    0.06
    Either
    0.06
    Activations Density 0.173%

    No Known Activations