© 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. 16606
    Prev
    Next
    INDEX
    Explanations

    novel therapeutic

    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
    éģ¥
    -0.09
     Herrn
    -0.07
    ggio
    -0.07
    ,next
    -0.07
    éģ¥éģ¥
    -0.07
    arium
    -0.07
    ÑĢони
    -0.07
    olino
    -0.07
    onio
    -0.07
    Existing
    -0.07
    POSITIVE LOGITS
     redundant
    0.08
     simplified
    0.07
    çĿģå¼Ģ
    0.07
     redundancy
    0.07
    ç´ĦæĿŁ
    0.07
    缣
    0.06
    ç«ĭå¼ı
    0.06
    _pixels
    0.06
    è±ĨèħIJ
    0.06
     redund
    0.06
    Activations Density 0.007%

    No Known Activations