© 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. 64920
    Prev
    Next
    INDEX
    Explanations

    art, automobiles, morbidity, Ustad, plastic arts

    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
     $($
    -0.07
    talk
    -0.07
    ooth
    -0.07
    üglich
    -0.06
    tee
    -0.06
    нÑĤÑĥ
    -0.06
    ambut
    -0.06
    Credentials
    -0.06
    uhan
    -0.06
    Been
    -0.06
    POSITIVE LOGITS
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.08
    æĮĩçļĦæĺ¯
    0.08
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    enet
    0.07
    panse
    0.07
    attia
    0.07
     yani
    0.07
    дÑĢÑı
    0.07
    ¿
    0.07
    Ñħе
    0.07
    Activations Density 0.228%

    No Known Activations