© 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. 10930
    Prev
    Next
    INDEX
    Explanations

    sustainability study

    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
    åĸľæĢĴåĵĢä¹IJ
    -0.07
    afari
    -0.07
    onsor
    -0.07
    èIJ¨çī¹
    -0.07
    _Impl
    -0.06
    æݧ
    -0.06
    ay
    -0.06
    Expression
    -0.06
    çݩ游æĪı
    -0.06
    ipel
    -0.06
    POSITIVE LOGITS
    å¼ķçĶ¨
    0.07
    å¸ĥéĩĮ
    0.07
    sthrough
    0.07
    iler
    0.06
    angani
    0.06
    erden
    0.06
    riz
    0.06
    ritti
    0.06
    个ä¸ĵä¸ļ
    0.06
    _utc
    0.06
    Activations Density 0.012%

    No Known Activations