© 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. 18789
    Prev
    Next
    INDEX
    Explanations

    therapy-induced

    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
    icino
    -0.07
    bsp
    -0.07
    æµĭå®ļ仪
    -0.07
    ings
    -0.07
    å¤§åľ°
    -0.07
    ubl
    -0.07
    ï¾Ł
    -0.06
    ivate
    -0.06
    QueryString
    -0.06
    eldon
    -0.06
    POSITIVE LOGITS
    ä¸įåĢ¦
    0.08
    .hr
    0.07
     Cấp
    0.07
    ialized
    0.07
    alendar
    0.07
    ales
    0.07
    .currentTime
    0.07
    herits
    0.07
    abbage
    0.07
    ळà¥ĩ
    0.07
    Activations Density 0.002%

    No Known Activations