© 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. 49045
    Prev
    Next
    INDEX
    Explanations

    King and I, : PHP, uc Phuong

    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
    uchu
    -0.09
    å¨ģ士
    -0.07
    ignum
    -0.07
    麻麻
    -0.07
    ruž
    -0.07
    াবà§ĩ
    -0.07
    KeyType
    -0.07
    ä¸Ńéĵģ
    -0.07
    orma
    -0.07
    æĿİå°ı
    -0.07
    POSITIVE LOGITS
    azio
    0.07
    èĪ
    0.07
    æĬ±è´Ł
    0.07
    æ´ŀåºŃ
    0.06
    æĪĺ
    0.06
    agine
    0.06
    éĥ½æĬĬ
    0.06
    ottle
    0.06
    otto
    0.06
     unins
    0.06
    Activations Density 0.017%

    No Known Activations