© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14247
    Prev
    Next
    INDEX
    Explanations

    changing and evolving

    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
    plr
    -0.08
    IZZ
    -0.07
    èĻ½çĦ¶ä¸įæĺ¯
    -0.07
     seri
    -0.07
    (series
    -0.07
    诣
    -0.07
    æľīç»Ħç»ĩ
    -0.07
     hao
    -0.07
    ffc
    -0.07
     série
    -0.07
    POSITIVE LOGITS
     changing
    0.14
     evolving
    0.14
    éļıçĿĢ
    0.13
    éļıçĿĢæŶéĹ´çļĦæݨ移
    0.13
    changing
    0.13
    åĬ¨æĢģ
    0.13
    ä¸įæĸŃåıĺåĮĸ
    0.12
    Changing
    0.12
    éļ¨èijĹ
    0.12
     updating
    0.12
    Activations Density 0.147%

    No Known Activations