© 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. 19716
    Prev
    Next
    INDEX
    Explanations

    numbers and specific code tokens

    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
    aje
    -0.07
     |_
    -0.07
     neither
    -0.06
    æĭįä¸ĭ
    -0.06
     Grill
    -0.06
    ä¿Ŀè¯ģåħ¶
    -0.06
    éis
    -0.06
     Ñģоединений
    -0.06
     differential
    -0.06
    iration
    -0.06
    POSITIVE LOGITS
    ITE
    0.08
    udev
    0.07
    лип
    0.07
    Å¡Å¥
    0.07
    .readyState
    0.07
    odom
    0.07
    ç«£
    0.07
    enment
    0.07
     Äı
    0.07
    _APB
    0.07
    Activations Density 0.001%

    No Known Activations