© 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. 12481
    Prev
    Next
    INDEX
    Explanations

    refractive index

    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
    agai
    -0.08
    trand
    -0.08
    isca
    -0.08
    assandra
    -0.08
    çĩİ
    -0.08
    urras
    -0.08
    номи
    -0.07
    ossa
    -0.07
    ç±»åĴĮ
    -0.07
    ools
    -0.07
    POSITIVE LOGITS
     optical
    0.07
     Optical
    0.07
    (speed
    0.07
    ammer
    0.07
    çİ»
    0.06
     optics
    0.06
    缸
    0.06
     crystal
    0.06
    å¯Ĩ
    0.06
    éĢıæĺİ度
    0.06
    Activations Density 0.002%

    No Known Activations