© 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. 3013
    Prev
    Next
    INDEX
    Explanations

    followed by with

    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
    çļĦåŃ©åŃIJ
    -0.12
    ìĿĺ
    -0.11
    çļĦåıĺåĮĸ
    -0.10
    çļĦ表çİ°
    -0.10
    çļĦä¿¡æģ¯
    -0.10
    çļĦæķĪæŀľ
    -0.10
    çļĦæķĻèĤ²
    -0.10
    çļĦåѦçĶŁ
    -0.10
    çļĦ管çIJĨ
    -0.10
    çļĦéĢŁåº¦
    -0.10
    POSITIVE LOGITS
     with
    0.15
     vỼi
    0.14
    à¸ģัà¸ļ
    0.13
    with
    0.13
    çļĦ
    0.13
     dengan
    0.13
    ÛĮ
    0.13
    _with
    0.12
    nya
    0.12
     ×¢×Ŀ
    0.12
    Activations Density 0.660%

    No Known Activations