© 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. 50445
    Prev
    Next
    INDEX
    Explanations

    said, asked, or stated

    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
    tryk
    -0.08
    åĪĽéĢłä¸Ģ个
    -0.08
    ä¸įè§ĦèĮĥ
    -0.07
    çĻ½æ°´
    -0.07
    ä¸įå®īåħ¨
    -0.07
    ä¸įä½Ĩ
    -0.07
    æ¯Ķè¾ĥ容æĺĵ
    -0.07
    çĥŃéŨæIJľç´¢
    -0.07
     tell
    -0.07
    .opensource
    -0.07
    POSITIVE LOGITS
    éĢ²ä¸ĢæŃ¥
    0.07
    "":
    0.07
     further
    0.07
    éĢĻé»ŀ
    0.07
    强è°ĥ
    0.07
    è¿Ľä¸ĢæŃ¥
    0.07
     concluding
    0.07
     emphas
    0.07
    achs
    0.07
    uffed
    0.07
    Activations Density 0.001%

    No Known Activations