© 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. 39236
    Prev
    Next
    INDEX
    Explanations

    numbers or sequences

    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
     rigorous
    -0.07
     rigor
    -0.07
    毫ä¸į
    -0.06
     reaff
    -0.06
     justru
    -0.06
    kej
    -0.06
    fulness
    -0.06
     ÙħÙĪÙģÙĤ
    -0.06
     profound
    -0.06
    ä¸Ģçķª
    -0.06
    POSITIVE LOGITS
    æľīæķĪæݧåĪ¶
    0.09
     деÑĢж
    0.09
    åľ¨çº¿è§Ĥçľĭ
    0.08
    вÑı
    0.08
    uzzi
    0.08
    ":[{"
    0.08
    çļĦæݧåĪ¶
    0.08
     holdings
    0.08
    recent
    0.08
    .Generated
    0.08
    Activations Density 0.001%

    No Known Activations