© 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. 2915
    Prev
    Next
    INDEX
    Explanations

    temp

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

    No Comments

    Negative Logits
     Jeremy
    -17.50
    Jeremy
    -17.25
     derivative
    -16.63
     arrangement
    -15.44
    pole
    -14.88
    伯
    -14.50
     arrangements
    -14.25
     BER
    -14.13
     Harr
    -14.00
    oder
    -13.94
    POSITIVE LOGITS
     temp
    68.50
    temp
    63.00
    =temp
    62.75
    (temp
    61.50
    [temp
    60.50
     Temp
    57.00
    Temp
    56.75
    	temp
    55.75
    .temp
    55.75
    ,temp
    54.50
    Activations Density 0.025%

    No Known Activations