© 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. 15135
    Prev
    Next
    INDEX
    Explanations

    compound word suffixes

    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
    çļĦæ¯ıä¸Ģ
    -0.10
    çļĦåIJĦ个
    -0.09
     ÏĢεÏģιÏĥÏĥÏĮÏĦε
    -0.08
    çļĦèĥĮåIJİ
    -0.08
    bane
    -0.08
     каÑĩ
    -0.08
    incon
    -0.08
    ensk
    -0.08
    endre
    -0.08
    õi
    -0.08
    POSITIVE LOGITS
    çļĦä¸Ģç§į
    0.13
    çļĦä¸Ģç±»
    0.09
    çļĦä¸Ģ種
    0.09
    çļĦä¸Ģç§įæĸ¹å¼ı
    0.08
    ä¸ŃçļĦä¸Ģç§į
    0.08
    çļĦä¸Ģ款
    0.07
    çļĦä¸Ģéģĵ
    0.07
    çļĦä¸Ģéĥ¨
    0.07
    çļĦä¸Ģ座
    0.07
    åı¦å¤ĸä¸Ģç§į
    0.07
    Activations Density 0.159%

    No Known Activations