© 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. 64312
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    imo
    -0.08
    atson
    -0.08
    ä¸įåĢ¦
    -0.08
    éģµå®Īä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½
    -0.08
     fortal
    -0.08
    nitt
    -0.08
     Critical
    -0.07
    esco
    -0.07
    å½·
    -0.07
    кома
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
    ster
    0.07
    丽
    0.06
    渡åģĩ
    0.06
    ley
    0.06
    豫
    0.06
    ç¥IJ
    0.06
    Pe
    0.06
    æľīä½ķ
    0.06
     statu
    0.06
    Activations Density 0.001%

    No Known Activations