© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15574
    Prev
    Next
    INDEX
    Explanations

    say practice

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

    No Comments

    Negative Logits
    icopt
    -17.25
     Damage
    -15.88
     Structures
    -15.31
    archives
    -15.19
    damage
    -15.13
     structures
    -14.94
    _attrib
    -14.94
    PEG
    -14.88
    城市群
    -14.75
    rypto
    -14.63
    POSITIVE LOGITS
    实践
    28.75
    实践活动
    27.50
     practice
    26.63
    社会实践
    26.00
     Practice
    24.63
    实践经验
    24.25
    的生活
    24.00
    现实生活
    23.38
     practise
    23.25
     prat
    23.13
    Activations Density 0.303%

    No Known Activations