© 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. 17285
    Prev
    Next
    INDEX
    Explanations

    parentheses and commas

    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
    erne
    -0.08
    rike
    -0.07
    ÃŃas
    -0.07
    ç±ģ
    -0.07
    iesel
    -0.07
    OTOS
    -0.07
    ÃŃa
    -0.07
    CEL
    -0.07
    çļĪ
    -0.07
    Ả
    -0.07
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.07
    adget
    0.07
    åIJĪåIJĮæŶ
    0.07
    ож
    0.07
    evoli
    0.07
    åĴĮåIJĦ
    0.07
    ead
    0.07
    åŁİ乡建设
    0.07
    æ¾Ħ
    0.07
    evil
    0.06
    Activations Density 0.018%

    No Known Activations