© 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. 18274
    Prev
    Next
    INDEX
    Explanations

    consistency and repetition

    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
     halves
    -0.08
    orm
    -0.08
    asa
    -0.07
    赶快
    -0.07
    ÙıÙħÙĴ
    -0.07
    æĩĤå¾ĹäºĨ
    -0.07
    etz
    -0.07
    OG
    -0.07
    ision
    -0.07
    zy
    -0.07
    POSITIVE LOGITS
     подÑĢÑıд
    0.09
    次çļĦ
    0.09
    ively
    0.09
    ä¸įæĸŃçļĦ
    0.08
    ently
    0.08
     consistently
    0.08
     successive
    0.08
     menerus
    0.08
    peated
    0.08
    è¿ŀç»ŃçļĦ
    0.08
    Activations Density 0.243%

    No Known Activations