© 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. 15056
    Prev
    Next
    INDEX
    Explanations

    production and synthesis

    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
    è¿Ľç«Ļ
    -0.07
     Williamson
    -0.07
    оÑĢи
    -0.07
    çĮ
    -0.07
    ignored
    -0.07
    æľī太å¤ļ
    -0.07
    ehand
    -0.07
    ffect
    -0.06
    天ä¸ĭ
    -0.06
    anganan
    -0.06
    POSITIVE LOGITS
     emits
    0.08
    产éĩı
    0.08
    éĩĬæĶ¾åĩº
    0.08
    åIJĪæĪIJ
    0.08
     emitir
    0.08
    æºIJæºIJ
    0.08
    çĶŁäº§
    0.08
    éĩĬæĶ¾
    0.08
    åIJĪæĪIJçļĦ
    0.08
    åĤ¨å¤ĩ
    0.07
    Activations Density 0.201%

    No Known Activations