© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57078
    Prev
    Next
    INDEX
    Explanations

    math and programming syntax

    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
    aliza
    -0.08
    maÃŁen
    -0.07
    alha
    -0.07
    вани
    -0.07
    vár
    -0.07
     '~/
    -0.07
     zato
    -0.07
    itario
    -0.07
    uchi
    -0.07
    affer
    -0.07
    POSITIVE LOGITS
     **ãĢIJ
    0.07
    ulu
    0.07
    èĩ
    0.06
    DITION
    0.06
     Flach
    0.06
     );
    0.06
     ad
    0.06
    åĪ©
    0.06
    iserie
    0.06
     ${(
    0.06
    Activations Density 0.001%

    No Known Activations