© 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. 51762
    Prev
    Next
    INDEX
    Explanations

    numbers, days, and prices

    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
    èĢĮå½±åĵį
    -0.08
    èĢĮ导èĩ´
    -0.08
     differently
    -0.08
    ä»İèĢĮ导èĩ´
    -0.08
    èĢĮæĺĵ
    -0.08
    èĢĮéĢłæĪIJ
    -0.07
    å¾Īå°ıçļĦ
    -0.07
    å¿ħé¡»çĶ±
    -0.07
    以èĩ´
    -0.07
    ä¸Ģå®ļè¦ģ
    -0.07
    POSITIVE LOGITS
    æīįæĺ¯
    0.11
    æĺ¯åĶ¯ä¸Ģ
    0.09
    å±ħå¤ļ
    0.09
    ä¸ºå®ľ
    0.09
     suffice
    0.09
    æīįæĺ¯æľĢ
    0.08
    æľĢåIJĪéĢĤ
    0.08
    æĺ¯æľĢ
    0.08
    为é¦ĸ
    0.08
     suff
    0.08
    Activations Density 0.037%

    No Known Activations