© 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. 30891
    Prev
    Next
    INDEX
    Explanations

    effect or commencement

    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
    ulich
    -0.10
    cripción
    -0.09
    ergestellt
    -0.09
    uÅĤ
    -0.08
    áĥª
    -0.08
    aum
    -0.08
     inzwischen
    -0.08
    ɵ
    -0.08
    manship
    -0.08
     mittlerweile
    -0.08
    POSITIVE LOGITS
    aneous
    0.09
    aneously
    0.09
    ly
    0.08
    à¸Ĺัà¸Ļ
    0.08
    ities
    0.07
    ë°Ķë¡ľ
    0.07
    ledged
    0.07
    mente
    0.07
    ness
    0.07
    oyer
    0.07
    Activations Density 0.017%

    No Known Activations