© 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. 56773
    Prev
    Next
    INDEX
    Explanations

    flight control, path, procedures

    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
    ../../../
    -0.09
    æļĤè¡Įè§Ħå®ļ
    -0.08
    Ł
    -0.07
     Ñģобой
    -0.07
    বাদ
    -0.07
    orer
    -0.07
    iled
    -0.07
    पà¥Ĥरà¥įण
    -0.07
    à¸łà¸´
    -0.07
    ../../
    -0.07
    POSITIVE LOGITS
    æĹłéĺ»
    0.08
    uard
    0.08
    zeug
    0.08
    ograma
    0.08
    ยย
    0.08
    lassen
    0.07
    ãĥ¤ãĥ¼
    0.07
    ç¿Ķ
    0.07
    ceau
    0.07
     aérea
    0.07
    Activations Density 0.037%

    No Known Activations