© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13948
    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
    opper
    -16.50
    广告服务
    -15.94
     solve
    -15.25
    城乡
    -15.25
    Draft
    -15.25
    oux
    -15.19
     Municip
    -15.19
     Draft
    -15.13
     Glas
    -15.13
    乡土
    -15.06
    POSITIVE LOGITS
    记忆
    44.50
    的记忆
    40.50
     memory
    40.50
    mem
    39.00
    Mem
    38.50
     memories
    38.25
    (mem
    37.25
     mem
    37.00
    _mem
    36.75
     Memory
    36.75
    Activations Density 0.555%

    No Known Activations