© 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. 18151
    Prev
    Next
    INDEX
    Explanations

    beginning or start

    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
    gev
    -0.08
    åħ¶éĹ´
    -0.07
    ä¸Ģä¸įå°ıå¿ĥ
    -0.07
    erstra
    -0.07
    iaan
    -0.07
    angan
    -0.07
    IPA
    -0.07
    ipa
    -0.07
    ="""
    -0.07
    oire
    -0.07
    POSITIVE LOGITS
    åĴĮ第äºĮ
    0.11
     tiên
    0.10
    FIRST
    0.09
    头
    0.08
    æĹ©
    0.08
    第ä¸Ģ项
    0.08
    (first
    0.08
    第ä¸Ģ
    0.08
    æĹ©æĹ©
    0.08
    头çļĦ
    0.08
    Activations Density 0.241%

    No Known Activations