© 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. 45406
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or code snippets

    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
    ynos
    -0.09
    è¦ģä¸įçĦ¶
    -0.08
    ayet
    -0.08
    dür
    -0.08
    ITHER
    -0.08
    leit
    -0.08
    æ²³æ¹ĸ
    -0.08
    ISI
    -0.08
    cher
    -0.08
    )!
    -0.08
    POSITIVE LOGITS
    als
    0.07
    //
    0.06
    0.06
     Kand
    0.06
    强
    0.06
    ...(
    0.06
    åģĩ
    0.06
    ement
    0.06
     ric
    0.06
    éļ»
    0.06
    Activations Density 0.096%

    No Known Activations