© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42546
    Prev
    Next
    INDEX
    Explanations

    adjectives describing qualities or characteristics

    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
    à¸Ħวาม
    -0.07
    italia
    -0.07
    able
    -0.06
    .uk
    -0.06
    ikka
    -0.06
    ives
    -0.06
    æĺ¯åı¯
    -0.06
    é¡į
    -0.06
    ermann
    -0.06
    à¸Ńัà¸Ļ
    -0.06
    POSITIVE LOGITS
    [Index
    0.09
    allery
    0.07
    gun
    0.07
    æłijä¸Ģ
    0.07
    "class
    0.07
    yonel
    0.07
     formativo
    0.07
    yet
    0.07
     voire
    0.07
    eix
    0.07
    Activations Density 0.099%

    No Known Activations