© 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. 13680
    Prev
    Next
    INDEX
    Explanations

    identifiers followed by text fragments

    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
    azionali
    -0.08
    ancel
    -0.08
    itut
    -0.07
    kring
    -0.07
    ÏĦήÏģιο
    -0.07
    æĬ¬éłŃ
    -0.07
    >An
    -0.07
    enerator
    -0.07
    ermal
    -0.07
    fel
    -0.07
    POSITIVE LOGITS
    é¡¿
    0.08
    iom
    0.07
    éłĵ
    0.07
    å¾Ĵ
    0.07
    iem
    0.07
    deb
    0.07
    endus
    0.07
    ONI
    0.06
    ç¥ŀ
    0.06
    imon
    0.06
    Activations Density 0.041%

    No Known Activations