© 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. 4062
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    artz
    -0.09
    ucar
    -0.08
     sciences
    -0.07
    æľīèī²
    -0.07
    æĥ³è¯´
    -0.07
     TimeZone
    -0.07
    ×Ĺ׳×ķ
    -0.07
    Altern
    -0.07
    失
    -0.07
    ingo
    -0.07
    POSITIVE LOGITS
    âĢij
    0.08
     âĢ¦
    0.07
    inte
    0.07
     sit
    0.07
    %S
    0.06
    æĿ¥è¿ĩ
    0.06
    gil
    0.06
    idak
    0.06
     ’
    0.06
    uwd
    0.06
    Activations Density 0.001%

    No Known Activations