© 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. 46563
    Prev
    Next
    INDEX
    Explanations

    real estate transactions: buyer, seller, agent, closing, sale

    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
    airo
    -0.07
    åĶ®ç¥¨
    -0.07
    é¢ľ
    -0.07
    æĮºèĥ¸
    -0.07
    èµĦè´¹
    -0.07
    å®ĮæĪIJä»»åĬ¡
    -0.06
    认éĶĻ
    -0.06
    å¤ĸåĮħ
    -0.06
    å¹´åį¡
    -0.06
     едини
    -0.06
    POSITIVE LOGITS
    éĿĵ
    0.09
    è¿ĩæĪ·
    0.08
     Buyer
    0.08
    ç²¾è£ħ
    0.08
    ç²¾è£ħä¿®
    0.08
     lender
    0.08
     buyer
    0.08
    æĪijçĪ±æĪij家
    0.08
    -git
    0.07
    çľĭæĪ¿
    0.07
    Activations Density 0.111%

    No Known Activations