© 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. 62344
    Prev
    Next
    INDEX
    Explanations

    real estate and housing market

    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
    å·¥åķĨæĪ·
    -0.08
    .Scope
    -0.07
    undry
    -0.07
    举éģĵ
    -0.07
    rita
    -0.07
    è¿Ľåĩºåı£ä¿¡çĶ¨
    -0.07
    protocols
    -0.06
     Laboratories
    -0.06
    ä¼ı
    -0.06
    poke
    -0.06
    POSITIVE LOGITS
    æĪ·åŀĭ
    0.11
     residential
    0.11
    èĩªä½ı
    0.10
     mortgage
    0.10
    mort
    0.10
    çļĦåľŁåľ°
    0.10
     mortgages
    0.09
     property
    0.09
    å®īå±ħ
    0.09
    å°ıæĪ·åŀĭ
    0.09
    Activations Density 0.273%

    No Known Activations