© 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. 1692
    Prev
    Next
    INDEX
    Explanations

    budget

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

    No Comments

    Negative Logits
     diet
    -19.00
    电路
    -18.13
    builders
    -18.13
    	cursor
    -17.50
    diet
    -17.25
     Calendar
    -17.13
    -di
    -16.63
    菜单
    -16.63
     cursor
    -16.63
     Diet
    -16.50
    POSITIVE LOGITS
    law
    20.88
     lawful
    20.38
    lights
    19.38
     law
    18.63
     Phelps
    18.38
     smoked
    17.63
     Law
    17.13
    SM
    16.63
    物理学
    16.50
    -law
    16.25
    Activations Density 0.115%

    No Known Activations