© 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. 58172
    Prev
    Next
    INDEX
    Explanations

    most + superlative adjective

    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
    isht
    -0.09
    çļĦå°±æĺ¯
    -0.08
    innen
    -0.08
    /MIT
    -0.08
    halb
    -0.08
    idamente
    -0.07
    stagram
    -0.07
     Microsystems
    -0.07
    teras
    -0.07
    ลà¸Ńà¸ģ
    -0.07
    POSITIVE LOGITS
    ow
    0.08
    eenth
    0.08
    ambique
    0.08
    ŀ
    0.08
    /all
    0.07
    аÑĤоÑĩно
    0.07
    новен
    0.07
    æĥħåĨµä¸ĭ
    0.07
    reatment
    0.07
    afa
    0.07
    Activations Density 0.058%

    No Known Activations