© 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. 15353
    Prev
    Next
    INDEX
    Explanations

    [hex] => ,

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

    No Comments

    Negative Logits
    STAR
    -16.50
     SWAT
    -16.50
     SWT
    -16.38
     LOT
    -16.00
     Ortiz
    -16.00
     STAR
    -15.88
    _STAR
    -15.81
    LOT
    -15.75
     Norwich
    -15.44
     Estonia
    -15.38
    POSITIVE LOGITS
    pare
    15.75
    缓
    15.00
    ded
    14.50
     pud
    14.44
    膝
    14.31
    -d
    14.19
    色
    14.19
     Lê
    14.06
    ana
    14.06
    蠹
    13.94
    Activations Density 0.014%

    No Known Activations