© 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. 1820
    Prev
    Next
    INDEX
    Explanations

    ECG

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

    No Comments

    Negative Logits
     artist
    -15.31
    TV
    -15.19
    card
    -15.06
    艺术家
    -15.00
     UnityEngine
    -15.00
     Europa
    -14.75
     Card
    -14.75
     math
    -14.63
    Artist
    -14.50
    urb
    -14.31
    POSITIVE LOGITS
    (po
    19.25
    ше
    19.25
    abbit
    18.63
    秦国
    17.75
    snake
    17.25
    希腊
    16.63
    	pc
    16.50
    _po
    16.50
     Greece
    16.38
     MONEY
    16.25
    Activations Density 0.254%

    No Known Activations