© 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. 15117
    Prev
    Next
    INDEX
    Explanations

    say "2"

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

    No Comments

    Negative Logits
    ту
    -20.13
    wang
    -19.88
     Ton
    -19.63
    MG
    -19.50
    Hung
    -19.38
     Tango
    -19.38
     Tong
    -19.25
     Sund
    -19.13
    TON
    -19.13
     MG
    -18.88
    POSITIVE LOGITS
    花
    14.63
    迹
    14.25
    なり
    13.81
    霈
    13.13
     Adv
    13.06
    (sk
    13.06
    和服务
    13.00
     Ripple
    12.75
    闪闪
    12.56
    REE
    12.38
    Activations Density 0.046%

    No Known Activations