© 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. 28865
    Prev
    Next
    INDEX
    Explanations

    of noun phrases

    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
    à¹Ĩ
    -0.08
    engar
    -0.07
    cio
    -0.07
    æĸĩæijĺ
    -0.07
    æĺ¯ä½ł
    -0.07
    emic
    -0.07
    çĻ¾æĪĺ
    -0.06
    ÛĮÙĨÚ¯
    -0.06
    edis
    -0.06
    ÛĮتÛĮ
    -0.06
    POSITIVE LOGITS
    /rem
    0.12
    /rec
    0.10
    /rest
    0.10
    /up
    0.09
    /testing
    0.09
    /install
    0.09
    /ref
    0.09
     ÐĴами
    0.09
    ä¸İç»´æĬ¤
    0.09
     kembali
    0.09
    Activations Density 0.498%

    No Known Activations