© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14390
    Prev
    Next
    INDEX
    Explanations

    proper nouns

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

    No Comments

    Negative Logits
     Titan
    -21.25
    高尔
    -21.13
    stan
    -19.38
     Ferr
    -17.75
     Oliv
    -17.38
    Titan
    -16.75
    olumn
    -16.63
    柏
    -16.63
    賢
    -16.50
    .indent
    -16.38
    POSITIVE LOGITS
    �
    19.88
     cascade
    16.13
     Lyons
    16.00
    兆
    16.00
     Burst
    16.00
    常州
    15.63
     Casc
    15.31
    包子
    14.94
     burst
    14.75
     Ramsey
    14.75
    Activations Density 1.324%

    No Known Activations