© 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. 38596
    Prev
    Next
    INDEX
    Explanations

    table names, variable names, code structure

    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
    orate
    -0.08
    ÙĪÙĨات
    -0.08
    ardi
    -0.07
    eming
    -0.07
    _MAGIC
    -0.07
    amakan
    -0.07
    ardy
    -0.07
    ereg
    -0.07
    illot
    -0.07
    arton
    -0.07
    POSITIVE LOGITS
     direct
    0.06
    buk
    0.06
    ",{
    0.05
     determin
    0.05
    zÄĥ
    0.05
    æĹ©äºĽ
    0.05
     master
    0.05
    ÃŃs
    0.05
    ulong
    0.05
    åĴĮè§ĦèĮĥ
    0.05
    Activations Density 0.003%

    No Known Activations