© 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. 38534
    Prev
    Next
    INDEX
    Explanations

    study of mechanism

    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
    ưỡng
    -0.08
    ocator
    -0.07
    度éĩı
    -0.07
     اÙĦÙĪØ·ÙĨ
    -0.07
    átk
    -0.07
    HWND
    -0.07
    ÑĮми
    -0.07
    ensions
    -0.07
    aeda
    -0.07
    اصÙĦ
    -0.07
    POSITIVE LOGITS
    æŃ¥éª¤
    0.08
    åİĨç¨ĭ
    0.08
    -path
    0.07
     involving
    0.07
     steps
    0.07
     Painter
    0.07
     Lair
    0.07
     Path
    0.07
    (es
    0.07
    ural
    0.07
    Activations Density 0.025%

    No Known Activations