© 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. 50800
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
    æ¡
    -0.08
    ody
    -0.07
    uzzi
    -0.07
    ç½Ĺå¾·
    -0.07
    ols
    -0.07
    [input
    -0.07
    æĻļ
    -0.07
    à§Ī
    -0.07
    æĪĸå¤ļ
    -0.07
    èĬ
    -0.07
    POSITIVE LOGITS
    館
    0.07
    æ¯ĶåĪ«äºº
    0.07
    åIJijèį£
    0.07
    é¦Ĩ
    0.06
    VIC
    0.06
    AIT
    0.06
    ç»ĻåĪ«äºº
    0.06
    upert
    0.06
     CIT
    0.06
    lings
    0.06
    Activations Density 0.002%

    No Known Activations