© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 2247
    Prev
    Next
    INDEX
    Explanations

    temporary

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

    No Comments

    Negative Logits
    ��
    -16.13
     gut
    -15.38
    oton
    -15.06
     gutter
    -14.56
     meth
    -14.56
    習
    -14.50
    macros
    -14.38
    ottom
    -14.13
    utton
    -14.13
    meth
    -14.06
    POSITIVE LOGITS
    temp
    77.50
     temp
    77.00
     Temp
    74.50
    =temp
    72.50
    Temp
    71.00
    (temp
    70.50
     tmp
    68.50
    临时
    68.50
    [temp
    68.00
    	temp
    67.50
    Activations Density 0.221%

    No Known Activations