© 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. 2781
    Prev
    Next
    INDEX
    Explanations

    say "poly"

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

    No Comments

    Negative Logits
    .ret
    -16.88
    .Ret
    -16.13
    Wil
    -15.56
    -rec
    -15.06
     Tenn
    -15.00
    Boom
    -14.88
    Harness
    -14.81
     intim
    -14.56
     Ret
    -14.56
     mirrored
    -14.38
    POSITIVE LOGITS
     poly
    96.50
    poly
    88.00
     Poly
    87.50
    Poly
    84.00
    (poly
    82.50
    _poly
    73.00
    .poly
    70.00
    聚
    70.00
     polymer
    49.00
     polygon
    44.25
    Activations Density 0.107%

    No Known Activations