© 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. 19901
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ied
    -0.08
    iny
    -0.07
    orro
    -0.07
    pond
    -0.07
    ÑĨеп
    -0.07
    軸
    -0.07
    ê¼
    -0.07
     xÃŃ
    -0.06
    engen
    -0.06
     пÑĢеда
    -0.06
    POSITIVE LOGITS
    tv
    0.07
    ategorical
    0.07
    ä¹ĭæķ°
    0.07
    è´£
    0.07
    ornings
    0.07
    GLfloat
    0.07
    个èĤ¡
    0.07
    iola
    0.06
    å°Ķå¾·
    0.06
    åħ»
    0.06
    Activations Density 0.017%

    No Known Activations