© 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. 60171
    Prev
    Next
    INDEX
    Explanations

    numbers as durations, percentages, or dates

    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
    hl
    -0.07
    æģ¯
    -0.07
     NOT
    -0.07
    èĻ½çĦ¶æĺ¯
    -0.07
    æīĢåIJij
    -0.07
    oph
    -0.07
    гиÑħ
    -0.06
    пÑĢави
    -0.06
    pr
    -0.06
    l
    -0.06
    POSITIVE LOGITS
    åľ¨åİ¿
    0.08
     Laurea
    0.08
    неÑĨ
    0.08
    éħĮ
    0.07
    emor
    0.07
    ç§ĭæľĪ
    0.07
    ãĥŁãĥ³ãĤ°
    0.07
    é½¢
    0.07
    çĥŃéŨæݨèįIJ
    0.07
    èł»
    0.07
    Activations Density 0.004%

    No Known Activations