© 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. 26621
    Prev
    Next
    INDEX
    Explanations

    latex mathematical symbols

    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
    è¡·å¿ĥ
    -0.07
    sWith
    -0.07
    ç«Ļ
    -0.06
    BufferSize
    -0.06
     tá»ĭch
    -0.06
    chart
    -0.06
    adona
    -0.06
    å°Ĩè¿ĻäºĽ
    -0.06
    eras
    -0.06
    èĩªçĦ¶èĢĮ
    -0.06
    POSITIVE LOGITS
    اش
    0.08
    尼迪
    0.07
    满æĺ¯
    0.07
    ä»ĸ们已ç»ı
    0.07
    æľªæľī
    0.07
    é¹Ń
    0.07
    è¦ĥ
    0.07
    ãĥķãĤ©
    0.07
    èIJ±
    0.07
    objc
    0.07
    Activations Density 0.001%

    No Known Activations