© 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. 55307
    Prev
    Next
    INDEX
    Explanations

    author information containing superscript numbers

    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
    ä¹ĭ交
    -0.07
    æĿ¥è¿ĩ
    -0.07
    ola
    -0.07
    okka
    -0.07
    å½¼æѤ
    -0.07
    peror
    -0.07
    letin
    -0.06
     urmÄĥ
    -0.06
    ائÙĤ
    -0.06
    amel
    -0.06
    POSITIVE LOGITS
    èĢĮå¦Ĥä»Ĭ
    0.07
    -fw
    0.07
    ÙĨاÙĩ
    0.07
    /archive
    0.06
    iller
    0.06
    èĢĮçİ°åľ¨
    0.06
    è¿Ļ次活åĬ¨
    0.06
    compress
    0.06
    è±
    0.06
    決
    0.06
    Activations Density 0.037%

    No Known Activations