© 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. 15618
    Prev
    Next
    INDEX
    Explanations

    say "photo"

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

    No Comments

    Negative Logits
    okit
    -24.38
    瓮
    -19.63
     Hog
    -19.63
    费
    -17.88
    glas
    -17.63
    reur
    -17.25
     clam
    -17.13
    Gr
    -16.88
    urus
    -16.75
     gr
    -16.63
    POSITIVE LOGITS
    phot
    16.63
    穿透
    16.00
    ipro
    15.88
    圆形
    15.06
     photographer
    15.06
    摄影师
    15.06
     phot
    15.00
     Deserialize
    14.88
     Circle
    14.81
    烙
    14.81
    Activations Density 0.394%

    No Known Activations