© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14904
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    �
    -20.50
     Burst
    -17.25
     Lyons
    -17.13
    常州
    -17.13
     cascade
    -16.88
    兆
    -16.63
     Ramsey
    -16.50
    包子
    -16.25
     Casc
    -16.25
     fries
    -16.13
    POSITIVE LOGITS
     Titan
    20.50
    高尔
    19.13
     Ferr
    17.50
    stan
    17.00
     Oliv
    16.50
    indent
    16.25
    olumn
    16.00
    钻
    15.88
    柏
    15.75
     drill
    15.69
    Activations Density 1.272%

    No Known Activations