© 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. 21028
    Prev
    Next
    INDEX
    Explanations

    common sentence beginnings

    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
    bor
    -0.07
    è´®
    -0.07
    åĤ¨
    -0.06
    iller
    -0.06
    try
    -0.06
    iale
    -0.06
    à¹Ģà¸Ķียว
    -0.06
    å¿ħå®ļ
    -0.06
    ilder
    -0.06
    å¦ĩ
    -0.06
    POSITIVE LOGITS
     insp
    0.07
    æĹ¥ä»¥ä¸Ĭ
    0.07
    ÐijÐł
    0.07
    ém
    0.07
    iren
    0.07
    shaw
    0.07
    人ä¸Ģ
    0.07
    æĹ¥æŃ¢
    0.07
    åĪĬ
    0.07
     Abbott
    0.06
    Activations Density 0.381%

    No Known Activations