© 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. 15770
    Prev
    Next
    INDEX
    Explanations

    axis labels and data

    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¸įä¸ĭ
    -0.08
    anger
    -0.08
    esson
    -0.07
    ietta
    -0.07
     phẩm
    -0.07
    etti
    -0.07
    æIJľ
    -0.07
    chini
    -0.07
    人马
    -0.07
    ims
    -0.07
    POSITIVE LOGITS
    erland
    0.07
    xFE
    0.06
     input
    0.06
    ÑħÑĢо
    0.06
     x
    0.06
    åĪºæ¿Ģ
    0.06
    è´±
    0.06
     interval
    0.06
    .linspace
    0.06
    oling
    0.06
    Activations Density 0.030%

    No Known Activations