© 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. 4145
    Prev
    Next
    INDEX
    Explanations

    version information or reproduction steps

    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
    /cop
    -0.06
    ousy
    -0.06
     covered
    -0.06
    OfMonth
    -0.06
     purposes
    -0.06
    失æģĭ
    -0.06
    thag
    -0.06
    央
    -0.06
    uni
    -0.06
    .baidu
    -0.06
    POSITIVE LOGITS
     logs
    0.08
    åįĩ级åĪ°
    0.08
    æĩ
    0.08
    æĤ¬èµı
    0.08
     reproduce
    0.08
     Checklist
    0.08
     reproduced
    0.07
    logs
    0.07
     reproduk
    0.07
    å¸ĮæľĽåı¯ä»¥
    0.07
    Activations Density 1.350%

    No Known Activations