© 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. 51211
    Prev
    Next
    INDEX
    Explanations

    correctness and value

    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
    muz
    -0.08
    anei
    -0.08
    OLA
    -0.07
    åĨįä¹Łä¸įçĶ¨
    -0.07
    ipse
    -0.07
    uage
    -0.07
    ewis
    -0.07
    ä¸ĢèģĬ
    -0.07
    çļĦåĩłä¸ª
    -0.07
    uchos
    -0.07
    POSITIVE LOGITS
    åIJĦèĩª
    0.13
     equally
    0.13
    åIJĦæľīåIJĦ
    0.12
    åIJĦèĩªçļĦ
    0.11
    缺ä¸Ģä¸įåı¯
    0.11
    åIJĦæľī
    0.11
    ãģĿãĤĮãģŀãĤĮ
    0.10
    åIJĦåħ·
    0.09
     depending
    0.09
    ãģļãģ¤
    0.09
    Activations Density 0.057%

    No Known Activations