© 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. 60337
    Prev
    Next
    INDEX
    Explanations

    past tense or participial verb endings

    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
    **;
    -0.08
    "';
    -0.08
    æĥħ趣
    -0.07
    itere
    -0.07
    à¸ģุล
    -0.07
    eden
    -0.07
    poses
    -0.07
    اÙĨد
    -0.07
    ";
    -0.07
    pike
    -0.07
    POSITIVE LOGITS
    åıijå¸ĥäºİ
    0.07
    æĪIJç«ĭäºİ
    0.07
    .setCursor
    0.07
     Lass
    0.06
    lak
    0.06
    aeda
    0.06
    Inh
    0.06
    )return
    0.06
    åĪĽå»ºäºİ
    0.06
    å§ĭäºİ
    0.06
    Activations Density 0.828%

    No Known Activations