© 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. 24466
    Prev
    Next
    INDEX
    Explanations

    specific examples in context

    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
    еп
    -0.06
     end
    -0.06
     pure
    -0.06
    .diag
    -0.06
    å°Ķé¡¿
    -0.06
    ELA
    -0.06
     Annie
    -0.06
     Sl
    -0.06
    ä¸Ģè·¯
    -0.06
    åĽ¾åĨĮ
    -0.06
    POSITIVE LOGITS
    表çİ°åľ¨
    0.08
    å¤ļåŃĶ
    0.08
    rschein
    0.08
    éĤ¸
    0.07
    åľ³
    0.07
    prise
    0.07
    ä¸ĩ件
    0.07
    apter
    0.07
    æĿ¥ä¹ĭ
    0.07
    cesi
    0.07
    Activations Density 0.017%

    No Known Activations