© 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. 16746
    Prev
    Next
    INDEX
    Explanations

    without breaking MVVM

    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
    建设æĪIJ为
    -0.07
     gint
    -0.07
     dim
    -0.07
    åħ¼
    -0.07
    etz
    -0.07
     cron
    -0.07
    称
    -0.07
    ecker
    -0.07
     coverage
    -0.06
     Coverage
    -0.06
    POSITIVE LOGITS
    _allowed
    0.09
    åħģ许çļĦ
    0.09
    ä¸įç®Ĺ
    0.09
    ç®Ĺ
    0.08
    allowed
    0.08
     allowed
    0.08
    ç®Ĺæĺ¯
    0.08
    èĻ½çĦ¶ä¸įæĺ¯
    0.08
    ä¸įå±ŀäºİ
    0.08
     Allowed
    0.08
    Activations Density 0.041%

    No Known Activations