© 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. 55846
    Prev
    Next
    INDEX
    Explanations

    time or numbers

    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
    æģ¯æģ¯
    -0.07
    ศึà¸ģ
    -0.07
    æĹłæĢ¨æĹłæĤĶ
    -0.07
    ãģ«èĪĪ
    -0.06
    agu
    -0.06
    就说
    -0.06
    -tool
    -0.06
    crud
    -0.06
    arbe
    -0.06
    orsch
    -0.06
    POSITIVE LOGITS
    lemn
    0.08
     Helf
    0.08
    èĦ¯
    0.07
    ÙĪÙĩ
    0.07
    eles
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
    _inds
    0.07
    akhir
    0.07
    象çīĻ
    0.07
    森çļĦ
    0.07
    Activations Density 0.046%

    No Known Activations