© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14472
    Prev
    Next
    INDEX
    Explanations

    self‑reflection

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

    No Comments

    Negative Logits
    alent
    -15.75
    enet
    -15.69
    aland
    -15.25
    .fp
    -15.19
    ustomer
    -15.19
    zman
    -15.13
    bsite
    -15.13
    shape
    -15.00
     professional
    -14.69
    ฐาน
    -14.63
    POSITIVE LOGITS
    ragon
    15.06
    陨
    14.81
     péri
    14.25
     mouths
    14.13
    rift
    13.94
    毁灭
    13.81
    铿
    13.81
    lyn
    13.81
    双眼
    13.75
    趄
    13.63
    Activations Density 0.297%

    No Known Activations