© 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. 33913
    Prev
    Next
    INDEX
    Explanations

    code examples

    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
    opard
    -0.07
    nden
    -0.07
    æ°Ľ
    -0.06
    æĸij驳
    -0.06
    _variance
    -0.06
    mens
    -0.06
    çIJĨåĮĸ
    -0.06
    åľ¨èº«
    -0.06
    com
    -0.06
    caret
    -0.06
    POSITIVE LOGITS
    лÑĮка
    0.08
    {@
    0.08
    è°¨
    0.07
     ourselves
    0.07
    illas
    0.07
    åİŁåŀĭ
    0.07
    urator
    0.07
    åIJĮéģĵ
    0.07
    è¡·å¿ĥ
    0.07
    aim
    0.07
    Activations Density 0.005%

    No Known Activations