© 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. 56142
    Prev
    Next
    INDEX
    Explanations

    what happens next

    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
    ØĮ
    -0.09
    ï¼Į
    -0.08
     _______,
    -0.08
    ,
    -0.07
    µ¬
    -0.07
    ï¼ĮãĢĬ
    -0.07
     gesta
    -0.07
    #,
    -0.07
    æĽ´ç²¾å½©
    -0.07
    å¾Īå¥ĩæĢª
    -0.07
    POSITIVE LOGITS
     że
    0.07
    离
    0.07
     että
    0.06
    ;amp
    0.06
    im
    0.06
    ()?.
    0.06
     ÑĤо
    0.06
     cioè
    0.06
     których
    0.06
    ied
    0.06
    Activations Density 0.330%

    No Known Activations