© 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. 38342
    Prev
    Next
    INDEX
    Explanations

    Indonesian/Malay place names

    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
    te
    -0.11
    gen
    -0.11
    den
    -0.11
    ë¥łìĿĢ
    -0.11
    teen
    -0.10
    gang
    -0.10
    ga
    -0.10
    ges
    -0.10
    ণ
    -0.10
    craft
    -0.10
    POSITIVE LOGITS
    åijIJ
    0.25
    à§įড
    0.17
     belül
    0.16
    etwork
    0.15
    ormal
    0.15
    egative
    0.15
    ucle
    0.15
    exus
    0.15
    ecessary
    0.14
     keresztül
    0.14
    Activations Density 3.444%

    No Known Activations