© 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. 11492
    Prev
    Next
    INDEX
    Explanations

    et al. citations

    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
    kring
    -0.07
     Rolex
    -0.07
    ä¹İ
    -0.07
    ylum
    -0.06
    èµĶåģ¿éĩij
    -0.06
    Ñģами
    -0.06
    abouts
    -0.06
    peror
    -0.06
    轻轻ä¸Ģ
    -0.06
    pery
    -0.06
    POSITIVE LOGITS
    aes
    0.07
    à¹ģà¸Ħ
    0.07
    ofi
    0.07
    iou
    0.07
    ÑĩаÑĤки
    0.07
    erras
    0.06
     frags
    0.06
    ç¤İ
    0.06
    ÙĬÙĨÙĩ
    0.06
    itzer
    0.06
    Activations Density 0.189%

    No Known Activations