© 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. 3373
    Prev
    Next
    INDEX
    Explanations

    explanation

    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
    宣åĪ¤
    -0.06
    æk
    -0.06
    ä¼ı
    -0.06
     ...
    -0.06
    粧
    -0.06
     ill
    -0.06
    æ°Ľ
    -0.06
    dat
    -0.06
    Öģ
    -0.06
    kant
    -0.06
    POSITIVE LOGITS
    天ä¹ĭ
    0.10
    ayan
    0.08
    atten
    0.08
    ظة
    0.08
    äºİå¿ĥ
    0.08
     tenuto
    0.08
    ayah
    0.08
    å¤ł
    0.08
    åŁºäºİ
    0.08
    åĸľæĢĴåĵĢ
    0.07
    Activations Density 0.004%

    No Known Activations