© 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. 1740
    Prev
    Next
    INDEX
    Explanations

    written form

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

    No Comments

    Negative Logits
     orally
    -21.50
    digital
    -21.25
    口头
    -20.88
    文字
    -20.13
     oral
    -19.75
     psychological
    -19.13
    rus
    -19.00
     digital
    -19.00
    (ps
    -18.75
     financial
    -18.63
    POSITIVE LOGITS
    cth
    17.25
     coal
    15.38
     Coal
    15.00
    煤
    14.81
     Bj
    14.69
    胶
    14.50
     asthma
    14.38
    વ
    14.38
    海
    14.31
    锚
    13.88
    Activations Density 0.074%

    No Known Activations