© 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. 40406
    Prev
    Next
    INDEX
    Explanations

    numbers and decimals

    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
    åĴĭ
    -0.06
    oger
    -0.06
    à¹ģà¸Ķà¸ĩ
    -0.06
    梵
    -0.06
    oes
    -0.06
     Fat
    -0.05
     fat
    -0.05
     Ling
    -0.05
    gard
    -0.05
    .Col
    -0.05
    POSITIVE LOGITS
    ÙĩÙĨ
    0.08
     kau
    0.08
     Jup
    0.08
    виÑĩа
    0.08
    ìĿį
    0.08
    aneous
    0.07
    пелÑĮ
    0.07
    ÃŃba
    0.07
    .meta
    0.07
    丽èIJį
    0.07
    Activations Density 0.003%

    No Known Activations