© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4756
    Prev
    Next
    INDEX
    Explanations

    business or legal agreements and contracts

    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
    Negative Logits
    åĪ¤æĸŃ
    -0.06
    اعة
    -0.06
    æıIJåĢ¡
    -0.06
    pras
    -0.06
    Accessible
    -0.06
    ä¸įåĬł
    -0.06
    åĢ¡å¯¼
    -0.06
    åĪ¤åĪ«
    -0.05
    åĶij
    -0.05
    uster
    -0.05
    POSITIVE LOGITS
     agreements
    0.19
     agreement
    0.16
    åįıè®®
    0.15
    çŃ¾è®¢
    0.14
    åįıè®®çļĦ
    0.13
    åIJĪä½ľåįıè®®
    0.13
     ÑģоглаÑĪение
    0.13
    çŃ¾å®ļ
    0.13
    çŃ¾è®¢çļĦ
    0.13
     Agreement
    0.13
    Activations Density 0.329%

    No Known Activations