© 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. 7657
    Prev
    Next
    INDEX
    Explanations

    i'd followed by verb

    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
    ÏĤ
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    er
    -0.08
    ments
    -0.08
    Ùĩ
    -0.07
    ive
    -0.07
    ë¡ľ
    -0.07
    åĴĮ
    -0.07
    ////////////////////////////////////////////////////////////////
    -0.07
    ÙĬÙĨ
    -0.07
    POSITIVE LOGITS
    zelfde
    0.10
    ewise
    0.10
    ãĢħ
    0.09
    iab
    0.09
    erness
    0.09
    ä¹ĭ以
    0.08
    æĿ¥è¶Ĭ
    0.08
    äºİä¸Ģ
    0.08
    å§Ķä¼ļ
    0.08
    iog
    0.08
    Activations Density 0.042%

    No Known Activations