© 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. 61558
    Prev
    Next
    INDEX
    Explanations

    problem or issue

    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
    å®ĺæĸ¹åįļ客
    -0.07
     seperate
    -0.06
    令人
    -0.06
    ationale
    -0.06
    å®ĮæĪIJä»»åĬ¡
    -0.06
     عÙĦÙĬÙĥ
    -0.06
    èĿĻèĿł
    -0.06
    irat
    -0.06
    该åĮº
    -0.06
    åħ«æĪĴ
    -0.06
    POSITIVE LOGITS
     regarding
    0.08
    imaan
    0.08
     concerning
    0.08
    æĺ¯åħ³äºİ
    0.08
    çļĦæľīåħ³
    0.08
     riguardo
    0.07
     concernant
    0.07
    åħ³äºİ
    0.07
    åĭĥ
    0.07
     poleg
    0.07
    Activations Density 0.122%

    No Known Activations