© 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. 57678
    Prev
    Next
    INDEX
    Explanations

    sizeof expressions

    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
    ê¹IJ
    -0.08
    usia
    -0.08
    urm
    -0.08
    kende
    -0.08
    类产åĵģ
    -0.08
    ież
    -0.08
    adini
    -0.08
    wick
    -0.08
    wear
    -0.08
    iewicz
    -0.08
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.09
    d
    0.07
    itu
    0.06
    ä¹ĭå¤ļ
    0.06
    æĹ¥æŃ¢
    0.06
    ä¸įæŃ»
    0.06
    天çİĭ
    0.06
    ł
    0.06
     -
    0.06
    Ø´ÙĬØ©
    0.06
    Activations Density 0.011%

    No Known Activations