© 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. 33870
    Prev
    Next
    INDEX
    Explanations

    Australian places and origins

    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
    人类社ä¼ļ
    -0.09
    enschaft
    -0.08
    对人çļĦ
    -0.07
    oczyn
    -0.07
    ç¥ŀåħµ
    -0.07
    çݰ代社ä¼ļ
    -0.07
    erre
    -0.07
    мм
    -0.07
    nels
    -0.07
    à¹Ħว
    -0.07
    POSITIVE LOGITS
    æľ¬åľŁ
    0.20
     native
    0.15
    æľ¬åľ°
    0.14
    æľ¬åľ°çļĦ
    0.14
     indigenous
    0.13
     local
    0.13
    native
    0.12
     domestic
    0.12
    çī¹èī²çļĦ
    0.12
    local
    0.12
    Activations Density 0.739%

    No Known Activations