© 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. 16300
    Prev
    Next
    INDEX
    Explanations

    say hang

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

    No Comments

    Negative Logits
    辛辣
    -20.75
    arbon
    -20.63
    糖尿病
    -20.25
     diabetic
    -19.50
     chloride
    -18.88
    碳酸
    -18.63
     Carol
    -18.63
    regor
    -18.25
    碳
    -18.25
     carcin
    -18.13
    POSITIVE LOGITS
    挂
    19.75
    挂着
    18.75
    悬挂
    18.63
    挂在
    18.50
     settle
    18.38
     deposit
    18.13
    庭院
    17.88
    ADS
    17.38
    掛
    17.38
    仓
    17.25
    Activations Density 0.963%

    No Known Activations