© 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. 1627
    Prev
    Next
    INDEX
    Explanations

    Buddhist scripture

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

    No Comments

    Negative Logits
     Bearings
    -16.13
     Amazon
    -15.75
    材
    -14.88
    钢材
    -14.88
     Economics
    -14.00
    设计
    -13.94
     Piano
    -13.69
    ensor
    -13.63
    材料
    -13.44
     cars
    -13.31
    POSITIVE LOGITS
    电信
    20.63
    盐
    19.75
     salt
    19.38
    salt
    19.13
    动态
    18.88
    电
    18.63
     math
    18.38
    鹽
    18.00
     Digit
    17.63
    通话
    17.63
    Activations Density 0.242%

    No Known Activations