© 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. 15491
    Prev
    Next
    INDEX
    Explanations

    [non] => [-]

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

    No Comments

    Negative Logits
    风
    -18.88
     Sco
    -18.13
    風
    -17.50
     gió
    -16.88
    撞
    -16.63
    漆
    -16.50
     Brace
    -16.38
     phase
    -16.25
     Phase
    -15.63
    (phase
    -15.56
    POSITIVE LOGITS
    -US
    15.94
    _NT
    15.69
    -lo
    15.69
    SSIP
    15.38
    erton
    15.06
    -NLS
    14.94
    uyên
    14.88
     nett
    14.69
    ervlet
    14.69
    嵊
    14.63
    Activations Density 0.031%

    No Known Activations