© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 748
    Prev
    Next
    INDEX
    Explanations

    say SP

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

    No Comments

    Negative Logits
    湖南省
    -22.75
     CA
    -20.38
    MN
    -19.63
    云南省
    -19.38
     calcium
    -19.25
     Myanmar
    -18.75
     Caesar
    -18.50
     Romanian
    -18.50
    曹
    -18.38
    缅甸
    -18.38
    POSITIVE LOGITS
     SP
    53.75
    SP
    51.75
    (SP
    51.25
    	SP
    50.25
    .SP
    43.00
     SSP
    39.75
     PSP
    37.00
    _SP
    36.75
     MSP
    34.25
    SPA
    33.50
    Activations Density 0.146%

    No Known Activations