© 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. 42254
    Prev
    Next
    INDEX
    Explanations

    code comments and 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
    atica
    -0.10
    ity
    -0.08
    водÑĥ
    -0.08
    иÑİ
    -0.08
    onation
    -0.08
    اÙĪÙĨ
    -0.08
    acci
    -0.07
    ertino
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
    isContained
    -0.07
    POSITIVE LOGITS
    anco
    0.07
    BS
    0.06
    ìį¨
    0.06
    Ļ
    0.06
     Riz
    0.06
    phere
    0.06
    ÑĨева
    0.06
    ÑĨев
    0.06
    lc
    0.06
    æµ´
    0.06
    Activations Density 0.034%

    No Known Activations