© 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. 42289
    Prev
    Next
    INDEX
    Explanations

    Australia and Australian places

    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
     Detroit
    -0.08
    -0.08
    çĩķ
    -0.07
    çĩķå±±
    -0.07
    åĮĹ京å¸Ĥ
    -0.07
    山西
    -0.07
    太è¡Į
    -0.07
     Brussels
    -0.07
     Paris
    -0.06
     c
    -0.06
    POSITIVE LOGITS
     Tasmania
    0.18
     Australia
    0.18
    Australian
    0.17
     ÐIJвÑģÑĤÑĢа
    0.17
     NSW
    0.17
    Australia
    0.17
    澳洲
    0.17
     Australien
    0.17
    ustralian
    0.17
     Australian
    0.16
    Activations Density 0.621%

    No Known Activations