© 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. 20938
    Prev
    Next
    INDEX
    Explanations

    Names and years

    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
    isher
    -0.07
    大
    -0.07
    olution
    -0.07
    VS
    -0.07
    éĿŀ常容æĺĵ
    -0.07
    æĭħä¿Ŀ
    -0.07
    aiss
    -0.07
    çĦ¶å¤§
    -0.07
    大åıĺ
    -0.07
    ignan
    -0.07
    POSITIVE LOGITS
    вÑĤ
    0.07
    soever
    0.07
    emas
    0.06
     tepatnya
    0.06
    anten
    0.06
    adt
    0.06
     Te
    0.06
    ä¹ĭæľº
    0.06
    åķ¡
    0.06
    缸åħ³äº§åĵģ
    0.06
    Activations Density 0.008%

    No Known Activations