© 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. 61228
    Prev
    Next
    INDEX
    Explanations

    exit or return

    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
    ünst
    -0.08
    spl
    -0.07
    اء
    -0.07
    heed
    -0.07
     /*!
    -0.07
    ä¸ļ
    -0.07
    бÑĢи
    -0.07
     &$
    -0.07
     Kia
    -0.07
    çĨŁ
    -0.07
    POSITIVE LOGITS
    Ù¾ÛĮ
    0.07
    大åIJī
    0.06
    otyping
    0.06
    ä¸ĭæĸĩ
    0.06
    çŀ»
    0.06
    uko
    0.06
    ikkan
    0.06
    追æ±Ĥ
    0.06
    æ¤Ĵ
    0.06
    igor
    0.06
    Activations Density 0.012%

    No Known Activations