© 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. 1492
    Prev
    Next
    INDEX
    Explanations

    文学

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

    No Comments

    Negative Logits
    文学
    -53.25
    文學
    -48.75
     literary
    -40.75
     literature
    -39.75
     Literature
    -39.00
    Liter
    -34.75
     Literary
    -33.00
     литер
    -30.88
     литератур
    -30.75
     Lit
    -30.50
    POSITIVE LOGITS
    币
    17.88
    ино
    15.50
    GF
    14.69
    java
    14.25
    坝
    14.19
    GB
    13.81
    .java
    13.63
    io
    13.38
    lo
    13.19
     ARG
    13.00
    Activations Density 0.030%

    No Known Activations