© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31213
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or delimiters

    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
    isable
    -0.08
    åĽ¾æĸ¯
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
    izable
    -0.08
    istically
    -0.08
    ezu
    -0.07
    Ĵáŀ
    -0.07
    aab
    -0.07
    çļĦ人äºĭ
    -0.07
    åĽ¾çīĩç´łæĿIJ
    -0.07
    POSITIVE LOGITS
    ìĿĺ
    0.20
    ãģ®
    0.18
    çļĦ
    0.15
    çļĦæł¸å¿ĥ
    0.13
    çļĦå°±æĺ¯
    0.13
    çļĦå¤ļ
    0.13
    çļĦæĪij
    0.12
    çļĦç»ıæµİ
    0.12
    çļĦè¿ĩç¨ĭä¸Ń
    0.12
    çļĦæłĩåĩĨ
    0.12
    Activations Density 0.098%

    No Known Activations