© 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. 64159
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    .nih
    -0.09
    åħ¬åı¸äºİ
    -0.08
    ialized
    -0.07
    vincial
    -0.07
    اÙĨÙĬا
    -0.07
    imina
    -0.07
     Tempor
    -0.07
    erable
    -0.07
    à¸Īิ
    -0.07
    ],&
    -0.07
    POSITIVE LOGITS
    дей
    0.07
    idar
    0.07
     wyj
    0.06
    lacht
    0.06
    ong
    0.06
    çIJĨäºĭ
    0.06
    istar
    0.06
    _FORMAT
    0.06
    ç«ĭçļĦ
    0.06
    IJ
    0.06
    Activations Density 0.541%

    No Known Activations