© 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. 28738
    Prev
    Next
    INDEX
    Explanations

    King and I

    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
    ä¸Ģ举
    -0.08
     Caz
    -0.07
     Eugen
    -0.07
    ابع
    -0.07
    opian
    -0.07
    ä¸Ģ头
    -0.07
    ì§ģ
    -0.07
    facebook
    -0.06
    KS
    -0.06
    åľ¨çº¿çķĻè¨Ģ
    -0.06
    POSITIVE LOGITS
     Provided
    0.07
     strr
    0.07
     provided
    0.07
    provided
    0.07
    Provid
    0.07
    ear
    0.07
    blr
    0.07
    å¿ĺæĢĢ
    0.07
    waran
    0.07
     entrando
    0.07
    Activations Density 0.001%

    No Known Activations