© 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. 50618
    Prev
    Next
    INDEX
    Explanations

    consider the following

    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
    æ±Ĥç²¾
    -0.08
    enderung
    -0.08
    lasan
    -0.07
    æĽ²å¼ł
    -0.07
    losion
    -0.07
    ÑĩенÑĸ
    -0.07
    å¾ĢæľŁåĽŀ顾
    -0.07
    illot
    -0.07
    enaar
    -0.07
    endiri
    -0.07
    POSITIVE LOGITS
    æĥħå¢ĥ
    0.08
     hypothetical
    0.07
    è¿Ļæł·çļĦä¸Ģ个
    0.07
    ue
    0.07
    以ä¸Ģ
    0.07
     interessanti
    0.07
    è´¨éĩı为
    0.07
    èĬ±ä¸Ģ
    0.07
    _GLOBAL
    0.07
     scenario
    0.07
    Activations Density 0.109%

    No Known Activations