© 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. 40578
    Prev
    Next
    INDEX
    Explanations

    instance, spec, riding, fare, signatures, ROM, inventory, strain

    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
    hausen
    -0.07
    éĻħ
    -0.07
    keit
    -0.06
    ä¸Ģ空
    -0.06
    jec
    -0.06
    ÑĪни
    -0.06
    fone
    -0.06
    .Dispatch
    -0.06
    çľģäºĭ
    -0.06
    صÙĪر
    -0.06
    POSITIVE LOGITS
    ologies
    0.10
    /function
    0.08
    wap
    0.08
    sWith
    0.08
    -holder
    0.08
    สุà¸Ķà¸Ĺà¹īาย
    0.08
    elor
    0.08
    दार
    0.07
    åľ¨èº«
    0.07
    hou
    0.07
    Activations Density 0.277%

    No Known Activations