© 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. 47722
    Prev
    Next
    INDEX
    Explanations

    successive progressive gradual ascending

    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
    é«ĺæ°Ķ
    -0.07
    ä¸īæĸ¹
    -0.07
    èĬĤçļĦ
    -0.06
     Bande
    -0.06
     Block
    -0.06
    ä¸Ģç»ıåıijçİ°
    -0.06
    Block
    -0.06
     Kui
    -0.06
    çļĦä¸ĢéĿ¢
    -0.06
    izo
    -0.06
    POSITIVE LOGITS
     successive
    0.11
     progressively
    0.11
     gradual
    0.10
    æ¸IJè¿Ľ
    0.10
    ä¸įæĸŃåĬłå¤§
    0.10
    ä¸įæĸŃå¢ŀåĬł
    0.10
     Progressive
    0.09
     progressive
    0.09
    éĢIJæŃ¥
    0.09
    éĢIJæ¸IJ
    0.09
    Activations Density 0.005%

    No Known Activations