© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2300
    Prev
    Next
    INDEX
    Explanations

    say 温

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

    No Comments

    Negative Logits
    甲方
    -21.00
    乙方
    -20.25
    爸爸
    -19.13
    olon
    -17.13
     methyl
    -16.13
    mill
    -16.00
    meth
    -15.75
    Mill
    -15.44
     MIL
    -15.31
    甲
    -15.25
    POSITIVE LOGITS
    温
    72.00
     temp
    66.00
    =temp
    64.00
    [temp
    64.00
    temp
    63.50
    (temp
    63.50
    	temp
    57.50
    .temp
    57.25
    Temp
    56.25
     Temp
    56.00
    Activations Density 0.061%

    No Known Activations