© 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. 25870
    Prev
    Next
    INDEX
    Explanations

    programming constructs and file references

    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
    ä¸įåīį
    -0.07
    elts
    -0.07
    /vendors
    -0.07
    ills
    -0.07
    gens
    -0.07
     Sez
    -0.07
    ç³ĸå°¿
    -0.07
    ائÙħ
    -0.07
    åĴĮçłĶ究
    -0.07
    ÙĪÙħ
    -0.07
    POSITIVE LOGITS
    åı«åģļ
    0.08
     representing
    0.08
    æŀĦæĪIJçļĦ
    0.08
    称为
    0.07
    åı«
    0.07
    ified
    0.07
    æŀĦ
    0.07
    åģļ为
    0.07
     called
    0.07
    代表
    0.07
    Activations Density 0.294%

    No Known Activations