© 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. 51854
    Prev
    Next
    INDEX
    Explanations

    file extensions like .php .html

    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
    ï¼ģ**
    -0.07
    ุà¸ģ
    -0.07
    ])[
    -0.07
    %",
    -0.07
    YPD
    -0.07
    resh
    -0.07
    **(
    -0.07
    deal
    -0.07
    **”
    -0.07
    ÑĬÑı
    -0.07
    POSITIVE LOGITS
    ئÙĩ
    0.07
    潺
    0.07
    ãĥ¬ãĥ¼ãĥĪ
    0.07
    ä¿¡çĶ¨çŃī级
    0.07
    erei
    0.07
    çħ¤çģ°
    0.07
    ק×ķת
    0.07
     âĢķ
    0.06
    æĸ°åĬłåĿ¡
    0.06
    ENDING
    0.06
    Activations Density 0.003%

    No Known Activations