© 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. 29963
    Prev
    Next
    INDEX
    Explanations

    contrast and concession ("but")

    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
    ega
    -0.07
    лÑĮе
    -0.07
    /pi
    -0.07
     Pej
    -0.07
    edd
    -0.06
    å¦Ĥå®ŀ
    -0.06
    已累计
    -0.06
     Daun
    -0.06
    丹
    -0.06
    ardon
    -0.06
    POSITIVE LOGITS
    ,but
    0.15
    —but
    0.12
    ãģ¾ãģĻãģĮ
    0.12
    ä½Ĩå¦Ĥæŀľ
    0.12
    ãģ¾ãģĽãĤĵãģĮ
    0.11
    âĢ¦but
    0.11
    ãģĤãĤĬãģ¾ãģĻãģĮ
    0.11
     but
    0.11
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.11
    .but
    0.11
    Activations Density 0.597%

    No Known Activations