© 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. 33041
    Prev
    Next
    INDEX
    Explanations

    ionic, -ity, -oping, æĢ§

    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
    ings
    -0.14
    åĴĮ
    -0.14
    ypes
    -0.11
    ìĿĺ
    -0.11
    INGS
    -0.10
    çļĦç¡®æĺ¯
    -0.10
    ément
    -0.10
    åĴĮåIJĮåѦ
    -0.10
    خاÙĨÙĩ
    -0.09
    åĴĮæľīåħ³
    -0.09
    POSITIVE LOGITS
    åįģ足çļĦ
    0.11
    ALLY
    0.09
    ally
    0.09
    ality
    0.09
    åįģ足
    0.09
    强çļĦ
    0.09
    è´¨çļĦ
    0.08
    annon
    0.08
    ity
    0.08
    keit
    0.07
    Activations Density 0.004%

    No Known Activations