© 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. 15920
    Prev
    Next
    INDEX
    Explanations

    end of word punctuation

    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
    ena
    -0.07
    ania
    -0.06
     конеÑĩном
    -0.06
    esis
    -0.06
    ведено
    -0.06
    еÑĤка
    -0.06
    endo
    -0.06
    ore
    -0.06
    à¸ļà¸ļ
    -0.06
    öm
    -0.05
    POSITIVE LOGITS
    zinho
    0.09
    æĬŀ
    0.09
    ÑıÑĤа
    0.08
    icarbon
    0.07
    alik
    0.07
    ãģĺãĤģãģ¦
    0.07
    Ñĸз
    0.07
    ¿
    0.07
    ÑĸÑĢ
    0.07
    LBL
    0.07
    Activations Density 4.741%

    No Known Activations