© 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. 14375
    Prev
    Next
    INDEX
    Explanations

    say non‑ASCII

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

    No Comments

    Negative Logits
    _rc
    -17.25
     thả
    -16.50
     dissolved
    -16.38
    湖泊
    -16.38
     Washington
    -16.00
    安宁
    -15.94
     washington
    -15.88
     rc
    -15.81
    召回
    -15.75
    调查显示
    -15.69
    POSITIVE LOGITS
    kor
    17.50
    胼
    16.63
    星光
    16.13
    荜
    15.94
     kor
    15.56
    兵团
    15.31
     Rug
    14.56
    槿
    14.56
     Frid
    14.50
     pill
    14.44
    Activations Density 0.975%

    No Known Activations