© 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. 20443
    Prev
    Next
    INDEX
    Explanations

    unique and different

    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
    ä¸į误
    -0.09
    ä»ĸ乡
    -0.07
    å·¥ç¨ĭä¸ĵä¸ļ
    -0.07
    ac
    -0.07
    é¥®é£Łä¹łæĥ¯
    -0.07
    游åĪĥæľīä½Ļ
    -0.06
    å¾Ħ缴
    -0.06
    ÑĥÑīеÑģÑĤво
    -0.06
    æķ°ä¸ª
    -0.06
     ambigu
    -0.06
    POSITIVE LOGITS
    æ¯ı次
    0.09
    éĥ½æľīä¸įåIJĮçļĦ
    0.09
     randomized
    0.09
    åĬ±
    0.08
     batches
    0.08
    éļıæľº
    0.08
    iates
    0.08
     batch
    0.08
    éĥ½ä¸įä¸Ģæł·
    0.08
    çĻ»å½ķæŁ¥çľĭ
    0.08
    Activations Density 0.037%

    No Known Activations