© 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. 61219
    Prev
    Next
    INDEX
    Explanations

    algebraic expressions

    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
    ç¾İ
    -0.07
    æ³ķ
    -0.07
    endis
    -0.07
    terna
    -0.07
    ç¼ĵ
    -0.07
     lẫn
    -0.06
    æĭĦ
    -0.06
    acent
    -0.06
    ube
    -0.06
    ffin
    -0.06
    POSITIVE LOGITS
    å²IJ
    0.08
    akit
    0.07
    amat
    0.07
    伦å¤ļ
    0.07
    çļĦèĥĮåIJİ
    0.07
    FromClass
    0.07
    afb
    0.07
    å¾·åĭĴ
    0.07
    apis
    0.06
    readonly
    0.06
    Activations Density 0.013%

    No Known Activations