© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14993
    Prev
    Next
    INDEX
    Explanations

    [phrase] => [acronym]

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

    No Comments

    Negative Logits
    ec
    -32.00
    éc
    -31.63
    ac
    -31.13
     Ec
    -30.63
    ecc
    -30.38
    Ec
    -30.13
     Zac
    -28.75
    ец
    -28.00
    (ac
    -27.88
    (nc
    -27.75
    POSITIVE LOGITS
    ワイ
    16.75
    燎
    15.00
    зу
    14.94
    吼
    14.75
    偃
    14.50
    gf
    14.44
    好莱
    14.38
    篷
    14.38
    岱
    14.38
    bast
    14.31
    Activations Density 0.035%

    No Known Activations