© 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. 14573
    Prev
    Next
    INDEX
    Explanations

    I have

    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
    weisen
    -0.07
    æľīæīĢ
    -0.07
    æīĢ以大家
    -0.07
    toString
    -0.07
    ä¼Ĺ人çļĦ
    -0.07
    çij¾
    -0.07
     fold
    -0.06
     fans
    -0.06
     sao
    -0.06
    оз
    -0.06
    POSITIVE LOGITS
    #@
    0.08
    elit
    0.08
    fid
    0.07
    uger
    0.07
    fle
    0.07
    fy
    0.07
    childs
    0.07
    /wp
    0.07
    _attached
    0.07
    bles
    0.07
    Activations Density 0.002%

    No Known Activations