© 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. 57548
    Prev
    Next
    INDEX
    Explanations

    -born American or Australian

    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
    æĭįæīĭ
    -0.08
    æ°¸åĴĮ
    -0.08
    ãģ©ãģĵãĤį
    -0.07
    ÙĩاÙħ
    -0.07
    ugt
    -0.07
     ê°ľìĦ¤
    -0.07
    å¥ĸçļĦ
    -0.07
    奨
    -0.07
    羡
    -0.07
    (loc
    -0.07
    POSITIVE LOGITS
     transferred
    0.13
     transfer
    0.11
     transferring
    0.11
    _transfer
    0.10
    Transfer
    0.10
    移æ¤į
    0.10
     transfers
    0.10
     Transfer
    0.10
    _TRANSFER
    0.10
    转移åĪ°
    0.10
    Activations Density 0.582%

    No Known Activations