© 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. 48352
    Prev
    Next
    INDEX
    Explanations

    intervention and its contexts

    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
    ģ
    -0.08
    avenport
    -0.07
    нок
    -0.07
    owers
    -0.07
    croft
    -0.07
    è¸Ĭ
    -0.06
    instein
    -0.06
    aring
    -0.06
    ารà¸ĸ
    -0.06
    ower
    -0.06
    POSITIVE LOGITS
    entions
    0.11
    å©¿
    0.10
    گرÛĮ
    0.09
    maat
    0.09
    æݪæĸ½çļĦ
    0.09
    emput
    0.09
    çľ¼å¸ĺ
    0.08
    ACLE
    0.08
    оÑĤÑĢе
    0.08
    ist
    0.08
    Activations Density 0.012%

    No Known Activations