© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    large data or amounts

    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
    大æĢĴ
    -0.10
    unj
    -0.10
    大è¯Ŀ
    -0.09
    onga
    -0.09
    rist
    -0.09
    大åı¯
    -0.09
    ÙĦد
    -0.09
    -Sah
    -0.09
    æķĻäºİ
    -0.09
    zelf
    -0.09
    POSITIVE LOGITS
    -hearted
    0.10
    -scale
    0.10
    ening
    0.09
     جدÙĭا
    0.09
    ish
    0.09
    ened
    0.09
    -headed
    0.09
     enough
    0.09
    heits
    0.09
     Ganze
    0.08
    Activations Density 0.055%

    No Known Activations