© 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. 15509
    Prev
    Next
    INDEX
    Explanations

    say iris

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

    No Comments

    Negative Logits
    萱
    -21.50
    阆
    -17.25
    蟠
    -17.13
     Camden
    -16.75
    赟
    -15.88
    EGA
    -15.81
    _rnn
    -15.69
    鞑
    -15.56
     EDT
    -15.50
    aea
    -15.44
    POSITIVE LOGITS
     Iris
    34.50
     iris
    31.50
     Irene
    31.00
    iks
    30.25
    ι
    30.25
    ไอ
    30.13
    iris
    29.88
    ici
    29.88
    ipi
    29.63
    Ι
    29.63
    Activations Density 7.033%

    No Known Activations