© 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. 60771
    Prev
    Next
    INDEX
    Explanations

    same, different, separate

    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
     uncompressed
    -0.07
    peror
    -0.07
    ä¾įéĥİ
    -0.07
    ä¸įå®ļ
    -0.07
     imitation
    -0.07
    ادرة
    -0.06
    iglia
    -0.06
    代ãĤıãĤĬãģ«
    -0.06
    ingga
    -0.06
    lng
    -0.06
    POSITIVE LOGITS
    åIJĮä¸Ģ
    0.18
    åIJĮä¸Ģ个
    0.17
    Same
    0.14
    缸åIJĮçļĦ
    0.14
     separate
    0.14
     SAME
    0.13
    .same
    0.13
    åIJĮãģĺ
    0.13
     seperate
    0.13
    same
    0.13
    Activations Density 0.188%

    No Known Activations