© 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. 57971
    Prev
    Next
    INDEX
    Explanations

    combobox related words

    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
    éªĩ
    -0.06
    INTERNAL
    -0.06
    .Cluster
    -0.06
    ابÙĤات
    -0.06
    awali
    -0.06
    ä¸Ģ家人
    -0.06
    /bg
    -0.06
     Prev
    -0.06
    arren
    -0.06
    Prev
    -0.06
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.14
    åIJĦèĩª
    0.14
     beiden
    0.11
    åIJĦæľī
    0.11
    ãģ©ãģ¡ãĤīãĤĤ
    0.10
     beide
    0.10
     kedua
    0.10
     ambos
    0.10
     обоиÑħ
    0.10
    ãģĿãĤĮãģŀãĤĮ
    0.09
    Activations Density 0.083%

    No Known Activations