© 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. 45515
    Prev
    Next
    INDEX
    Explanations

    lessons and learned experiences

    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
    详ç»Ĩæııè¿°
    -0.08
     Concep
    -0.07
    Æł
    -0.07
    .googleapis
    -0.07
    æĪij代表
    -0.07
    LAN
    -0.07
    ç®Ģåįķä»ĭç»į
    -0.07
    indices
    -0.07
    Describe
    -0.07
    æĥ³è±¡ä¸Ń
    -0.07
    POSITIVE LOGITS
    æķĻè®Ń
    0.15
     lesson
    0.14
     lessons
    0.13
    åIJ¯ç¤º
    0.12
    lesson
    0.11
     Lessons
    0.11
    Lesson
    0.11
    è¿Ļ个éģĵçIJĨ
    0.10
     Lesson
    0.10
    æĤŁ
    0.10
    Activations Density 0.106%

    No Known Activations