© 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. 16328
    Prev
    Next
    INDEX
    Explanations

    [hour] => [o]

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

    No Comments

    Negative Logits
     qs
    -22.88
    _qs
    -22.50
    qli
    -22.25
     qq
    -22.25
    iq
    -22.13
    qus
    -21.63
     qi
    -21.00
     Qi
    -20.63
     QQ
    -20.25
    qx
    -19.63
    POSITIVE LOGITS
     backpack
    22.00
     Backpack
    21.38
    锻
    19.63
    隧道
    19.63
    铠
    19.25
    装甲
    18.25
    舞
    18.13
     Kale
    18.00
    crypto
    17.75
    直升机
    17.75
    Activations Density 0.507%

    No Known Activations