© 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. 14907
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    Ark
    -20.75
    nar
    -20.13
    marshaller
    -19.25
    har
    -19.00
     Ark
    -18.88
     zar
    -18.50
     HAR
    -18.50
    iar
    -18.50
    mar
    -18.38
    tar
    -18.38
    POSITIVE LOGITS
    steen
    20.88
    SX
    20.25
    plen
    18.75
     Staten
    18.63
    斌
    18.50
    weep
    18.38
     SX
    18.13
    St
    17.88
    acen
    17.63
     McM
    17.50
    Activations Density 0.924%

    No Known Activations