© 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. 49718
    Prev
    Next
    INDEX
    Explanations

    duplicate or repeat

    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
    åĮ»éĻ¢åľ°åĿĢ
    -0.08
    aea
    -0.08
    åĴĮ解
    -0.08
    zol
    -0.07
    rika
    -0.07
    eho
    -0.07
    ëĭ¨ìĿĦ
    -0.07
    æħµ
    -0.07
    allen
    -0.07
    ho
    -0.07
    POSITIVE LOGITS
    éĩįå¤į
    0.11
    duplicate
    0.10
     Dup
    0.09
    uplicate
    0.09
     repeats
    0.09
    repeat
    0.09
     duplic
    0.09
     повÑĤоÑĢ
    0.09
    è¿°
    0.09
     repeat
    0.09
    Activations Density 0.043%

    No Known Activations