© 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. 38253
    Prev
    Next
    INDEX
    Explanations

    already

    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
    _NULL
    -0.07
    uevo
    -0.07
    pv
    -0.07
    ãĥĩãĤ£ãĤª
    -0.07
    enever
    -0.07
    zeigen
    -0.07
    Es
    -0.07
    æĺ¯åIJĹ
    -0.07
    tright
    -0.07
    ifax
    -0.07
    POSITIVE LOGITS
     too
    0.09
     already
    0.08
     Already
    0.08
    å·²ç»ıä¸įæĺ¯
    0.08
    rej
    0.08
    太
    0.07
    èĢĮä¸Ķ
    0.07
    ä¸į符åIJĪ
    0.07
    already
    0.07
    èĢĮä¸Ķæľī
    0.07
    Activations Density 0.044%

    No Known Activations