© 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. 2693
    Prev
    Next
    INDEX
    Explanations

    say memory

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

    No Comments

    Negative Logits
    (strip
    -15.63
    mat
    -15.25
     gen
    -15.00
    ,lat
    -14.69
    ickers
    -14.56
    .Gen
    -14.38
     mat
    -14.31
    [idx
    -14.25
    (idx
    -14.25
     Gen
    -14.06
    POSITIVE LOGITS
     mem
    66.00
    (mem
    65.50
    mem
    64.50
    记忆
    64.50
     Mem
    63.75
     remember
    63.75
    Mem
    63.75
     remembering
    62.50
    	mem
    62.00
     remembered
    61.00
    Activations Density 0.213%

    No Known Activations