© 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. 1939
    Prev
    Next
    INDEX
    Explanations

    popular free play understanding how to design

    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
    éĻį
    -0.07
    á»ĵi
    -0.06
     Study
    -0.06
     atleast
    -0.06
     bersangkutan
    -0.06
    èĩ³å°ijåľ¨
    -0.06
    çݲ
    -0.06
     Beverage
    -0.06
    æľ¬é¢ĺ
    -0.06
    decltype
    -0.06
    POSITIVE LOGITS
    èĭ¥æĺ¯
    0.09
    evas
    0.08
    æīĢ以å½ĵ
    0.08
    ç¦ģå¿Į
    0.08
    å¦Ĥæŀľåıªæĺ¯
    0.08
    _PROTO
    0.08
    ieger
    0.08
    isure
    0.08
    æĽ´å¤ļåħ³äºİ
    0.08
    _DECLS
    0.08
    Activations Density 0.005%

    No Known Activations