© 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. 22268
    Prev
    Next
    INDEX
    Explanations

    "Hello, World!"

    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
    ockey
    -0.07
    aire
    -0.07
    åħī顾
    -0.07
    chenk
    -0.07
     Citadel
    -0.07
    ä¿Ŀæľī
    -0.07
    elper
    -0.07
    rans
    -0.07
    enance
    -0.07
    illon
    -0.07
    POSITIVE LOGITS
    .freeze
    0.07
    æħ¨
    0.07
    ugas
    0.07
    ä»ĩ
    0.07
    ÙĪدÛĮ
    0.06
    apas
    0.06
    ick
    0.06
    Ùıس
    0.06
    请è¾ĵåħ¥
    0.06
    .gen
    0.06
    Activations Density 0.001%

    No Known Activations