© 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. 2722
    Prev
    Next
    INDEX
    Explanations

    say polymer

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

    No Comments

    Negative Logits
    Wil
    -18.25
     IMG
    -17.00
     Wil
    -16.38
    variant
    -15.56
    渌
    -15.25
    ˉ
    -14.88
    .rem
    -14.56
     mirrored
    -14.44
    avian
    -14.44
    strt
    -14.44
    POSITIVE LOGITS
     poly
    74.00
    聚
    71.00
    poly
    68.00
     Poly
    67.50
    Poly
    66.00
    (poly
    63.75
    _poly
    57.00
    .poly
    53.25
     polymer
    42.25
     Polymer
    37.75
    Activations Density 0.049%

    No Known Activations