© 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. 55734
    Prev
    Next
    INDEX
    Explanations

    speed of light, constants, throne

    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
    对æīĢ
    -0.07
    essi
    -0.07
    bud
    -0.07
     rejoint
    -0.07
    åIJijéĺ³
    -0.07
     xAxis
    -0.07
    xca
    -0.07
    ograd
    -0.07
    udies
    -0.07
    egree
    -0.07
    POSITIVE LOGITS
     constants
    0.09
     hằng
    0.07
     precision
    0.07
    æį¢ç®Ĺ
    0.07
     scientists
    0.07
    常éĩı
    0.07
    atos
    0.07
    unch
    0.07
     decimal
    0.07
     enormously
    0.07
    Activations Density 0.007%

    No Known Activations