© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1715
    Prev
    Next
    INDEX
    Explanations

    concrete

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

    No Comments

    Negative Logits
    CAC
    -21.38
    泥土
    -19.38
    混凝土
    -19.00
    法院
    -17.88
    _po
    -17.75
    汜
    -17.75
    .CV
    -17.38
    MQ
    -17.13
     mount
    -17.00
    货币
    -17.00
    POSITIVE LOGITS
    Mac
    15.38
     lambda
    15.06
     macOS
    14.69
    .mac
    14.56
     mac
    14.56
    (lambda
    14.50
    字母
    14.44
    俄
    14.44
     elect
    14.38
    urger
    14.38
    Activations Density 0.070%

    No Known Activations