© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16800
    Prev
    Next
    INDEX
    Explanations

    division remainder

    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
    帯
    -0.07
    лай
    -0.07
    åıĬéĶĢåĶ®
    -0.07
    ä¸İéĶĢåĶ®
    -0.07
    kr
    -0.07
    affer
    -0.07
    apus
    -0.06
    rana
    -0.06
    羣çļĦ好
    -0.06
    cken
    -0.06
    POSITIVE LOGITS
    ÙĩÙĨد
    0.08
    igham
    0.08
    ä¸ĩå²ģ
    0.08
    essar
    0.07
    渲
    0.07
    çľĭé½IJ
    0.07
    èµ·çłģ
    0.07
    acheter
    0.07
    éĿłå±±
    0.07
    éĻª
    0.06
    Activations Density 0.014%

    No Known Activations