© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 823
    Prev
    Next
    INDEX
    Explanations

    Method 3: TOP_POSITIVE_LOGITS all relate to fluorescence (flu, fluorescence, fluorescent, dye, 发光). Explanation: say fluorescence

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breeze
    -18.00
    甑
    -17.88
    weather
    -17.50
    椅子
    -17.50
    mtree
    -17.38
    杯子
    -17.25
    wind
    -17.13
    撂
    -17.00
    桌子上
    -17.00
    ApiClient
    -16.63
    POSITIVE LOGITS
    荧
    33.50
     fluorescence
    32.50
     fluor
    28.63
     Flu
    28.50
     fluores
    28.38
     fluorescent
    27.88
    flu
    26.38
     dye
    24.25
    发光
    23.88
     flu
    20.75
    Activations Density 0.088%

    No Known Activations