© 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. 55621
    Prev
    Next
    INDEX
    Explanations

    PHP variables, symbols, and inline code

    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
    Possible
    -0.06
    ho
    -0.06
    ROL
    -0.06
    ä¸Ģä¸ĭ
    -0.06
    белÑĮ
    -0.06
    èijĨ
    -0.06
    èĢIJå¾·
    -0.06
    CLU
    -0.06
    aved
    -0.06
     possible
    -0.06
    POSITIVE LOGITS
    arma
    0.08
    strup
    0.08
    ély
    0.07
    asin
    0.07
    croll
    0.07
    csi
    0.07
    ÑĤÑĩ
    0.07
    æ¡ij
    0.07
    .tom
    0.07
    ehme
    0.07
    Activations Density 0.002%

    No Known Activations