© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2392
    Prev
    Next
    INDEX
    Explanations

    say "½"

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

    No Comments

    Negative Logits
    (det
    -25.88
    det
    -25.63
     detector
    -25.38
     det
    -24.50
    检测
    -24.13
     detectors
    -24.00
    Detector
    -23.88
    detector
    -22.13
     Detector
    -21.63
    _DETECT
    -21.25
    POSITIVE LOGITS
    ¼
    31.63
    ½
    30.63
     ­
    28.13
    乙方
    27.88
    ¹
    26.50
    ­
    25.50
     �
    25.50
    ³
    24.50
    甲方
    24.50
    �
    24.25
    Activations Density 0.032%

    No Known Activations