© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14663
    Prev
    Next
    INDEX
    Explanations

    say commas

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

    No Comments

    Negative Logits
    巩
    -20.63
    icks
    -19.63
     minion
    -18.75
    麦克
    -18.75
    ilda
    -18.75
     McKay
    -18.13
    immutable
    -18.13
    micro
    -18.00
    时时彩
    -17.75
    GridColumn
    -17.50
    POSITIVE LOGITS
     Beth
    15.19
     pady
    14.56
     Bog
    14.50
    Bah
    14.44
     Beg
    14.38
     Bry
    14.25
     Lay
    14.25
     Sap
    14.19
     pov
    13.75
     Beng
    13.69
    Activations Density 0.164%

    No Known Activations