© 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. 42758
    Prev
    Next
    INDEX
    Explanations

    truth and mismatch

    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
    ê°ľ
    -0.07
    èĩªä¸»çŁ¥è¯Ĩ产æĿĥ
    -0.07
    venes
    -0.07
    æł¼ä¸½
    -0.07
    æĥŃæĦ§
    -0.07
     khép
    -0.07
    ORA
    -0.07
    INTERFACE
    -0.06
    باد
    -0.06
    .SQLite
    -0.06
    POSITIVE LOGITS
    izzas
    0.08
    apolis
    0.07
    æ²³ä¸Ń
    0.07
    ç½®ä¹ĭ
    0.07
    å¾Ļ
    0.07
     зло
    0.07
    ä¸Ģæ¡£
    0.07
    zcz
    0.07
    opard
    0.07
    amenta
    0.07
    Activations Density 0.007%

    No Known Activations