© 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. 2253
    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
     refinery
    -16.25
    Cond
    -15.31
     radical
    -15.06
    .Cond
    -14.94
     refunded
    -14.69
     Cond
    -14.13
    (strip
    -14.13
    KW
    -14.06
    (ref
    -13.81
    mars
    -13.81
    POSITIVE LOGITS
     memory
    91.50
     Memory
    85.00
    记忆
    82.50
    memory
    82.50
    Memory
    81.50
    (memory
    76.00
    -memory
    74.00
    的记忆
    73.50
    内存
    73.00
     mem
    72.50
    Activations Density 0.268%

    No Known Activations