© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1469
    Prev
    Next
    INDEX
    Explanations

    say "po"

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

    No Comments

    Negative Logits
    /cpu
    -21.75
    	cpu
    -21.00
    Paul
    -20.88
     CPU
    -20.13
     Paul
    -20.13
     paul
    -19.88
     cpu
    -19.75
    cpu
    -19.25
    CPU
    -18.88
     Muscle
    -18.75
    POSITIVE LOGITS
     poetry
    19.88
    -po
    18.75
    摄影师
    18.38
    诗人
    18.13
     Po
    18.13
     poetic
    17.88
    金融
    17.75
     graphene
    17.75
    ivet
    17.50
    商业银行
    17.38
    Activations Density 0.297%

    No Known Activations