© 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. 26473
    Prev
    Next
    INDEX
    Explanations

    sorting numbers in lists

    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
    uper
    -0.07
    å·¡è§Ĩ
    -0.06
    _CI
    -0.06
    æ¯ķä¸ļçļĦ
    -0.06
    ä¸īåĪĨ
    -0.06
    iog
    -0.06
    ä¸įå®ĮçļĦ
    -0.06
    _WARNING
    -0.06
    补缴
    -0.06
    .ci
    -0.06
    POSITIVE LOGITS
     etc
    0.08
    Ø«ÙĪر
    0.07
    etc
    0.07
    شد
    0.07
    _DU
    0.07
    (False
    0.07
    _unique
    0.07
     Voit
    0.07
     dll
    0.07
    สะ
    0.07
    Activations Density 0.051%

    No Known Activations