© 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. 13957
    Prev
    Next
    INDEX
    Explanations

    say stars

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

    No Comments

    Negative Logits
     strategy
    -17.38
    菠
    -17.25
    工程师
    -17.00
    -toast
    -16.88
    策略
    -16.38
    语言
    -16.25
    语气
    -16.25
     mond
    -16.25
     coverage
    -16.00
    ThreadPool
    -16.00
    POSITIVE LOGITS
    星座
    18.50
     stars
    18.25
     star
    17.75
     constellation
    16.88
    star
    16.38
    -stars
    16.00
    星空
    15.63
    -star
    15.31
     Stars
    15.31
    Stars
    15.25
    Activations Density 0.141%

    No Known Activations