© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7235
    Prev
    Next
    INDEX
    Explanations

    and Politics, and wearing, and tells

    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
    家æķĻ
    -0.08
    ritz
    -0.08
    rike
    -0.08
    league
    -0.07
    å¸Īé£İ
    -0.07
    ÙĦÙĤÙī
    -0.07
     ÐŁÐ¾Ñģо
    -0.07
    raf
    -0.07
    æ±Ĥç²¾
    -0.07
    imak
    -0.07
    POSITIVE LOGITS
     ultimately
    0.10
    æĢ»èĢĮè¨Ģä¹ĭ
    0.08
    çĶļèĩ³æĺ¯
    0.08
    Whatever
    0.08
     tháºŃm
    0.08
     simply
    0.08
    æĢ»ä¹ĭ
    0.08
    çĶļèĩ³
    0.07
    Ultimately
    0.07
     finally
    0.07
    Activations Density 0.224%

    No Known Activations