© 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. 1920
    Prev
    Next
    INDEX
    Explanations

    numbers and tens

    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
    culus
    -0.07
     {*
    -0.06
    assy
    -0.06
    注æĦıçļĦæĺ¯
    -0.06
    orary
    -0.06
    éĬŃ
    -0.06
    )._
    -0.06
    ến
    -0.06
    cy
    -0.06
    æİĮä¸Ĭ
    -0.06
    POSITIVE LOGITS
    ç»ıèIJ¥é¡¹çĽ®
    0.08
    æ»¡çĽ®
    0.08
    åĨ²
    0.08
    ие
    0.08
    ARAM
    0.08
    olin
    0.07
    è®¤è®¤çľŁçľŁ
    0.07
    :description
    0.07
    urf
    0.07
    ibat
    0.07
    Activations Density 0.003%

    No Known Activations