© 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. 2259
    Prev
    Next
    INDEX
    Explanations

    say struct

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

    No Comments

    Negative Logits
    ‒
    -18.13
     Ty
    -17.88
     Ken
    -17.38
     Administration
    -17.25
    Administration
    -16.88
     hexadecimal
    -16.75
     Jeremy
    -16.63
     Penal
    -16.25
     penalties
    -16.13
     dimensional
    -16.00
    POSITIVE LOGITS
     struct
    30.00
    struct
    24.50
     structs
    22.25
     str
    21.75
     mut
    19.75
    (str
    19.13
     fig
    19.00
    str
    18.75
     rep
    18.75
    	struct
    18.50
    Activations Density 0.022%

    No Known Activations